Posts by Category

FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents Permalink

Imene Kerboua, Sahar Omidi Shayegan, Megh Thakkar, Xing Han Lù, Léo Boisvert, Massimo Caccia, J’er’emy Espinas, Alexandre Aussem, V’eronique Eglin, Alexandre...

Semantic change in adults is not primarily a generational phenomenon. Permalink

Gaurav Kamath, Michelle Yang, Siva Reddy, Morgan Sonderegger, Dallas Card

The Promise of RL for Autoregressive Image Editing Permalink

Saba Ahmadi, Rabiul Awal, Ankur Sikarwar, Amirhossein Kazemnejad, Ge Ya Luo, Juan A. Rodriguez, Sai Rajeswar, Siva Reddy, Christopher Pal, Benno Krojer, Aish...

LineRetriever: Planning-Aware Observation Reduction for Web Agents Permalink

Imene Kerboua, Sahar Omidi Shayegan, Megh Thakkar, Xing Han Lù, Massimo Caccia, V’eronique Eglin, Alexandre Aussem, J’er’emy Espinas, Alexandre Lacoste

Build the web for agents, not agents for the web Permalink

Xing Han Lù, Gaurav Kamath, Marius Mosbach, Siva Reddy

Build the web for agents, not agents for the web Permalink

Xing Han Lù, Gaurav Kamath, Marius Mosbach, Siva Reddy

AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories Permalink

Xing Han Lù, Amirhossein Kazemnejad, Nicholas Meade, Arkil Patel, Dongchan Shin, Alejandra Zambrano, Karolina Stańczak, Peter Shaw, Christopher Pal, Siva Red...

Not All Data Are Unlearned Equally Permalink

Aravind Krishnan, Siva Reddy, Marius Mosbach

DeepSeek-R1 Thoughtology: Let’s think about LLM Reasoning Permalink

Sara Vera Marjanović, Arkil Patel, Vaibhav Adlakha, Milad Aghajohari, Parishad BehnamGhader, Mehar Bhatia, Aditi Khandelwal, Austin Kraft, Benno Krojer, Xing...

Exploiting Instruction-Following Retrievers for Malicious Information Retrieval Permalink

Parishad BehnamGhader, Nicholas Meade, Siva Reddy

SafeArena: Evaluating the Safety of Autonomous Web Agents Permalink

Ada Defne Tur, Nicholas Meade, Xing Han Lù, Alejandra Zambrano, Arkil Patel, Esin Durmus, Spandana Gella, Karolina Stańczak, Siva Reddy

Societal Alignment Frameworks Can Improve LLM Alignment Permalink

Karolina Sta’nczak, Nicholas Meade, Mehar Bhatia, Hattie Zhou, Konstantin Bottinger, Jeremy Barnes, Jason Stanley, Jessica Montgomery, Richard Zemel, Nicolas...

MMTEB: Massive Multilingual Text Embedding Benchmark Permalink

Kenneth C. Enevoldsen, Isaac Chung, Imene Kerboua, Márton Kardos, Ashwin Mathur, David Stap, Jay Gala, W. Siblini, Dominik Krzemi’nski, Genta Indra Winata, S...

Warmup Generations: A Task-Agnostic Approach for Guiding Sequence-to-Sequence Learning with Unsupervised Initial State Generation Permalink

Senyu Li, Zipeng Sun, Jiayi Wang, Xue Liu, Pontus Stenetorp, Siva Reddy, D. Adelani

Language Models Largely Exhibit Human-like Constituent Ordering Preferences Permalink

Not All Data Are Unlearned Equally Permalink

Aravind Krishnan, Siva Reddy, Marius Mosbach

How to Get Your LLM to Generate Challenging Problems for Evaluation Permalink

Arkil Patel, Siva Reddy, Dzmitry Bahdanau

ReTreever: Tree-based Coarse-to-Fine Representations for Retrieval Permalink

Shubham Gupta, Zichao Li, Tianyi Chen, Cem Subakan, Siva Reddy, Perouz Taslakian, Valentina Zantedeschi

The BrowserGym Ecosystem for Web Agent Research Permalink

Thibault Le Sellier De Chezelles, Maxime Gasse, Alexandre Lacoste, Alexandre Drouin, Massimo Caccia, L’eo Boisvert, Megh Thakkar, Tom Marty, Rim Assouel, Sah...

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks Permalink

Juan A. Rodriguez, Xiangru Jian, Siba Smarak Panigrahi, Tianyu Zhang, Aarash Feizi, Abhay Puri, Akshay Kalkunte, Franccois Savard, Ahmed Masry, Shravan Nayak...

Uhura: A Benchmark for Evaluating Scientific Question Answering and Truthfulness in Low-Resource African Languages Permalink

Edward Bayes, Israel Abebe Azime, Jesujoba Oluwadara Alabi, Jonas Kgomo, Tyna Eloundou, Elizabeth Proehl, Kai Chen, Imaan Khadir, Naome A. Etori, Shamsuddeen...

From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP Permalink

Marius Mosbach, Vagrant Gautam, Tomás Vergara Browne, Dietrich Klakow, Mor Geva

VinePPO: Refining Credit Assignment in RL Training of LLMs Permalink

Amirhossein Kazemnejad, Milad Aghajohari, Eva Portelance, Alessandro Sordoni, Siva Reddy, Aaron C. Courville, Nicolas Le Roux

Machine Translation Hallucination Detection for Low and High Resource Languages using Large Language Models Permalink

Kenza Benkirane, Laura Gongas, Shahar Pelles, Naomi Fuchs, Joshua Darmon, Pontus Stenetorp, David Ifeoluwa Adelani, Eduardo Sánchez, Meta

Faithfulness Measurable Masked Language Models Permalink

Andreas Madsen, Sarath Chandar, Siva Reddy

Benchmarking Vision Language Models for Cultural Understanding Permalink

Shravan Nayak, Kanishk Jain, Rabiul Awal, Siva Reddy, Sjoerd van Steenkiste, Lisa Anne Hendricks, Karolina Sta’nczak, Aishwarya Agrawal

Mitigating Translationese in Low-resource Languages: The Storyboard Approach Permalink

Garry Kuwanto, E. Urua, Priscilla Amuok, Shamsuddeen Hassan Muhammad, Anuoluwapo Aremu, V. Otiende, Loice Emma Nanyanga, T. Nyoike, A. D. Akpan, Nsima Ab Udo...

Are self-explanations from Large Language Models faithful? Permalink

Andreas Madsen, Sarath Chandar, Siva Reddy

Learning Action and Reasoning-Centric Image Editing from Videos and Simulations Permalink

Benno Krojer, Dheeraj Vattikonda, Luis Lara, Varun Jampani, Eva Portelance, Christopher Pal, Siva Reddy

Voices Unheard: NLP Resources and Models for Yorùbá Regional Dialects Permalink

Orevaoghene Ahia, Anuoluwapo Aremu, Diana Abagyan, Hila Gonen, David Ifeoluwa Adelani, D. Abolade, Noah A. Smith, Yulia Tsvetkov

Evaluating In-Context Learning of Libraries for Code Generation Permalink

Arkil Patel, Siva Reddy, Dzmitry Bahdanau, Pradeep Dasigi

Reframing linguistic bootstrapping as joint inference using visually-grounded grammar induction models Permalink

Eva Portelance, Siva Reddy, T. O’Donnell

Confabulation: The Surprising Value of Large Language Model Hallucinations Permalink

Peiqi Sui, Eamon Duede, Sophie Wu, Richard Jean So

IrokoBench: A New Benchmark for African Languages in the Age of Large Language Models Permalink

David Ifeoluwa Adelani, Jessica Ojo, Israel Abebe Azime, Zhuang Yun Jian, Jesujoba Oluwadara Alabi, Xuanli He, Millicent Ochieng, Sara Hooker, Andiswa Bukula...

Meta’s AI translation model embraces overlooked languages. Permalink

David Ifeoluwa Adelani

Scope Ambiguities in Large Language Models Permalink

Gaurav Kamath, Sebastian Schuster, Sowmya Vajjala, Siva Reddy

Interpretability Needs a New Paradigm Permalink

Andreas Madsen, Himabindu Lakkaraju, Siva Reddy, Sarath Chandar

Does Generative AI speak Nigerian-Pidgin?: Issues about Representativeness and Bias for Multilingualism in LLMs Permalink

David Ifeoluwa Adelani, A. S. Dougruoz, Iyanuoluwa Shode, Anuoluwapo Aremu

Comparing LLM prompting with Cross-lingual transfer performance on Indigenous and Low-resource Brazilian Languages Permalink

David Ifeoluwa Adelani, A. S. Dougruoz, Andr’e Coneglian, Atul Kr. Ojha

EkoHate: Abusive Language and Hate Speech Detection for Code-switched Political Discussions on Nigerian Twitter Permalink

Comfort Eseohen Ilevbare, Jesujoba Oluwadara Alabi, David Ifeoluwa Adelani, Firdous Damilola Bakare, O. B. Abiola, O. Adeyemo

Investigating Adversarial Trigger Transfer in Large Language Models Permalink

Nicholas Meade, Arkil Patel, Siva Reddy

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders Permalink

Parishad BehnamGhader, Vaibhav Adlakha, Marius Mosbach, Dzmitry Bahdanau, Nicolas Chapados, Siva Reddy

Scope Ambiguities in Large Language Models Permalink

Gaurav Kamath, Sebastian Schuster, Sowmya Vajjala, Siva Reddy

ANGOFA: Leveraging OFA Embedding Initialization and Synthetic Data for Angolan Language Model Permalink

Osvaldo Luamba Quinjica, David Ifeoluwa Adelani

WebLINX: Real-World Website Navigation with Multi-Turn Dialogue Permalink

Xing Han Lù, Zdeněk Kasner, Siva Reddy

The BrowserGym Ecosystem for Web Agent Research Permalink

Thibault Le Sellier De Chezelles, Maxime Gasse, Alexandre Lacoste, Alexandre Drouin, Massimo Caccia, L’eo Boisvert, Megh Thakkar, Tom Marty, Rim Assouel, Sah...

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks Permalink

Juan Rodriguez, Xiangru Jian, Siba Smarak Panigrahi, Tianyu Zhang, Aarash Feizi, Abhay Puri, Akshay Kalkunte, Franccois Savard, Ahmed Masry, Shravan Nayak, R...

A Compositional Typed Semantics for Universal Dependencies Permalink

Laurestine Bradford, T. O’Donnell, Siva Reddy

When does word order matter and when doesn’t it? Permalink

Xuanda Chen, T. O’Donnell, Siva Reddy

Are self-explanations from Large Language Models faithful? Permalink

Andreas Madsen, Sarath Chandar, Siva Reddy

Qualitative Code Suggestion: A Human-Centric Approach To Qualitative Coding Permalink

Cesare Spinoso-Di Piano, Samira Abbasgholizadeh Rahimi, Jackie Chi Kit Cheung

Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness Permalink

Zichao Li, Ines Arous, Siva Reddy, Jackie Chi Kit Cheung

AfriMTE and AfriCOMET: Enhancing COMET to Embrace Under-resourced African Languages Permalink

Jiayi Wang, David Ifeoluwa Adelani, Sweta Agrawal, Marek Masiak, Ricardo Rei, Eleftheria Briakou, Marine Carpuat, Xuanli He, Sofia Bourhim, Andiswa Bukula, M...

How good are Large Language Models on African Languages? Permalink

Jessica Ojo, Kelechi Ogueji, Pontus Stenetorp, David Ifeoluwa Adelani

MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretations Permalink

Arkil Patel, Satwik Bhattamishra, Siva Reddy, Dzmitry Bahdanau

In-Context Learning for Text Classification with Many Labels Permalink

Aristides Milios, Siva Reddy, Dzmitry Bahdanau

SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects Permalink

David Ifeoluwa Adelani, Hannah Liu, Xiaoyu Shen, Nikita Vassilyev, Jesujoba Oluwadara Alabi, Yanke Mao, Haonan Gao, Annie En-Shiun Lee

NaijaRC: A Multi-choice Reading Comprehension Dataset for Nigerian Languages Permalink

Anuoluwapo Aremu, Jesujoba Oluwadara Alabi, David Ifeoluwa Adelani

Consultative engagement of stakeholders toward a roadmap for African language technologies Permalink

Kathleen Siminyu, Jade Z. Abbott, Kólá Túbosún, Aremu Anuoluwapo, Blessing K. Sibanda, Kofi A. Yeboah, David Ifeoluwa Adelani, Masabata Mokgesi-Selinga, Fred...

Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering Permalink

Vaibhav Adlakha, Parishad BehnamGhader, Xing Han Lu, Nicholas Meade, Siva Reddy

The KITMUS Test: Evaluating Knowledge Integration from Multiple Sources Permalink

Akshatha Arodi, Martin Pömsl, Kaheer Suleman, Adam Trischler, Alexandra Olteanu, Jackie Chi Kit Cheung

ÌròyìnSpeech: A Multi-purpose Yorùbá Speech Corpus Permalink

Tolúlopé Ògúnrèmí, Kólá Túbosún, Aremu Anuoluwapo, Iroro Orife, David Ifeoluwa Adelani

Improving Language Plasticity via Pretraining with Active Forgetting Permalink

Yihong Chen, Kelly Marchisio, Roberta Raileanu, David Ifeoluwa Adelani, Pontus Stenetorp, Sebastian Riedel, Mikel Artetx

The Impact of Positional Encoding on Length Generalization in Transformers Permalink

Amirhossein Kazemnejad, Inkit Padhi, K. Ramamurthy, Payel Das, Siva Reddy

Are Diffusion Models Vision-And-Language Reasoners? Permalink

Benno Krojer, Elinor Poole-Dayan, Vikram S. Voleti, C. Pal, Siva Reddy

MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African languages Permalink

Cheikh M. Bamba Dione, David Ifeoluwa Adelani, Peter Nabende, Jesujoba Oluwadara Alabi, Thapelo Sindane, Happy Buzaaba, Shamsuddeen Hassan Muhammad, Chris C....

Syntactic Substitutability as Unsupervised Dependency Syntax Permalink

Jasper Jian, Siva Reddy

XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages Permalink

Sebastian Ruder, J. Clark, Alexander Gutkin, Mihir Kale, Min Ma, M. Nicosia, Shruti Rijhwani, Parker Riley, J. M. Sarr, Xinyi Wang, J. Wieting, Nitish Gupta,...

NollySenti: Leveraging Transfer Learning and Machine Translation for Nigerian Movie Sentiment Classification Permalink

Iyanuoluwa Shode, David Ifeoluwa Adelani, J. Peng, Anna Feldman

AfriQA: Cross-lingual Open-Retrieval Question Answering for African Languages Permalink

Odunayo Ogundepo, T. Gwadabe, Clara Rivera, J. Clark, Sebastian Ruder, David Ifeoluwa Adelani, Bonaventure F. P. Dossou, Abdoulahat Diop, Claytone Sikasote, ...

Vārta: A Large-Scale Headline-Generation Dataset for Indic Languages Permalink

Rahul Aralikatte, Ziling Cheng, Sumanth Doddapaneni, J. Cheung

StarCoder: may the source be with you! Permalink

Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, Qian Liu, Ev...

Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model Permalink

Parishad BehnamGhader, Santiago Miret, Siva Reddy

The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents Permalink

Xing Han Lu, Siva Reddy, Harm de Vries

Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP Permalink

Anya Belz, Craig Thomson, E. Reiter, Gavin Abercrombie, J. Alonso-Moral, Mohammad Arvan, J. Cheung, Mark Cieliebak, Elizabeth Clark, K. V. Deemter, Tanvi Din...

MasakhaNEWS: News Topic Classification for African languages Permalink

David Ifeoluwa Adelani, Marek Masiak, Israel Abebe Azime, Jesujoba Oluwadara Alabi, A. Tonja, Christine Mwase, Odunayo Ogundepo, Bonaventure F. P. Dossou, Ak...

SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval) Permalink

Shamsuddeen Hassan Muhammad, Idris Abdulmumin, Seid Muhie Yimam, David Ifeoluwa Adelani, I. Ahmad, N. Ousidhoum, A. Ayele, Saif M. Mohammad, Meriem Beloucif

How Useful are Educational Questions Generated by Large Language Models? Permalink

Sabina Elkins, E. Kochmar, J. Cheung, Iulian Serban

MphayaNER: Named Entity Recognition for Tshivenda Permalink

R. Mbuvha, David Ifeoluwa Adelani, Tendani Mutavhatsindi, Tshimangadzo Rakhuhu, A. Mauda, Tshifhiwa Joshua Maumela, Andisani Masindi, Seani Rananga, Vukosi M...

Varepsilon kú mask: Integrating Yorùbá cultural greetings into machine translation Permalink

Idris Akinade, Jesujoba Oluwadara Alabi, David Ifeoluwa Adelani, Clement Odoje, D. Klakow

Investigating Failures to Generalize for Coreference Resolution Models Permalink

Ian Porada, Alexandra Olteanu, Kaheer Suleman, A. Trischler, J. Cheung

The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset Permalink

Hugo Laurenccon, Lucile Saulnier, Thomas Wang, Christopher Akiki, Albert Villanova del Moral, Teven Le Scao, Leandro von Werra, Chenghao Mou, E. G. Ponferrad...

Systematic Rectification of Language Models via Dead-end Analysis Permalink

Mengyao Cao, Mehdi Fatemi, J. Cheung, S. Shabanian

AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages Permalink

Shamsuddeen Hassan Muhammad, Idris Abdulmumin, A. Ayele, N. Ousidhoum, David Ifeoluwa Adelani, Seid Muhie Yimam, I. Ahmad, Meriem Beloucif, Saif M. Mohammad,...

Learning with Rejection for Abstractive Text Summarization Permalink

Mengyao Cao, Yue Dong, Jingyi He, J. Cheung

Using In-Context Learning to Improve Dialogue Safety Permalink

Nicholas Meade, Spandana Gella, Devamanyu Hazarika, Prakhar Gupta, Di Jin, Siva Reddy, Yang Liu, Dilek Z. Hakkani-Tür

ε kú : Integrating YorùBá Cultural greetings into Machine Translation Permalink

Idris Akinade, Jesujoba Oluwadara Alabi, David Ifeoluwa Adelani, Clement Odoje, D. Klakow

A FRI S ENTI : A B ENCHMARK T WITTER S ENTIMENT A NALYSIS D ATASET FOR A FRICAN L ANGUAGES Permalink

Shamsuddeen Hassan Muhammad, Idris Abdulmumin, A. Ayele, N. Ousidhoum, David Ifeoluwa Adelani, Seid Muhie Yimam, Meriem Beloucif, Saif M. Mohammad, Sebastian...

Evaluating In-Context Learning of Libraries for Code Generation Permalink

Arkil Patel, Siva Reddy, Dzmitry Bahdanau, Pradeep Dasigi

Faithfulness Measurable Masked Language Models Permalink

Andreas Madsen, Siva Reddy, Sarath Chandar

Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering Permalink

Vaibhav Adlakha, Parishad BehnamGhader, Xing Han Lù, Nicholas Meade, Siva Reddy

Combining Parameter-efficient Modules for Task-level Generalisation Permalink

E. Ponti, Alessandro Sordoni, Y. Bengio, Siva Reddy

AfriMTE and AfriCOMET: Empowering COMET to Embrace Under-resourced African Languages Permalink

Jiayi Wang, David Ifeoluwa Adelani, Sweta Agrawal, Ricardo Rei, Eleftheria Briakou, Marine Carpuat, Marek Masiak, Xuanli He, Sofia Bourhim, Andiswa Bukula, M...

Findings of the 1st Shared Task on Multi-lingual Multi-task Information Retrieval at MRL 2023 Permalink

Francesco Tinner, David Ifeoluwa Adelani, Chris Emezue, Mammad Hajili, Omer Goldman, Muhammad Farid Adilazuarda, Muhammad Dehan Al Kautsar, Aziza Mirsaidova,...

Better Quality Pre-training Data and T5 Models for African Languages Permalink

Akintunde Oladipo, Mofetoluwa Adeyemi, Orevaoghene Ahia, A. Owodunni, Odunayo Ogundepo, David Ifeoluwa Adelani, Jimmy Lin

BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting Permalink

Zheng-Xin Yong, Hailey Schoelkopf, Niklas Muennighoff, Alham Fikri Aji, David Ifeoluwa Adelani, Khalid Almubarak, M Saiful Bari, Lintang Sutawika, Jungo Kasa...

The KITMUS Test: Evaluating Knowledge Integration from Multiple Sources Permalink

Akshatha Arodi, Martin Pömsl, Kaheer Suleman, A. Trischler, Alexandra Olteanu, J. Cheung

BLOOM: A 176B-Parameter Open-Access Multilingual Language Model Permalink

Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili’c, Daniel Hesslow, Roman Castagn’e, A. Luccioni, François Yvon, Matthias Gallé, J. To...

The Curious Case of Absolute Position Embeddings Permalink

Koustuv Sinha, Amirhossein Kazemnejad, Siva Reddy, Joelle Pineau, Dieuwke Hupkes, Adina Williams

MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition Permalink

David Ifeoluwa Adelani, Graham Neubig, Sebastian Ruder, Shruti Rijhwani, Michael Beukman, Chester Palen-Michel, Constantine Lignos, Jesujoba Oluwadara Alabi,...

Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining Permalink

Andreas Madsen, Nicholas Meade, Vaibhav Adlakha, Siva Reddy

BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus Permalink

Josh Meyer, David Ifeoluwa Adelani, Edresson Casanova, A. Oktem, Daniel Whitenack Julian Weber, Salomon Kabongo KABENAMUALU, Elizabeth Salesky, Iroro Orife, ...

Post-hoc Interpretability for Neural NLP: A Survey Permalink

Andreas Madsen, Siva Reddy, Sarath Chandar

TOKEN is a MASK: Few-shot Named Entity Recognition with Pre-trained Language Models Permalink

A. Davody, David Ifeoluwa Adelani, Thomas Kleinbauer, D. Klakow

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models Permalink

Big Bench

Few-shot Question Generation for Personalized Feedback in Intelligent Tutoring Systems Permalink

Devang Kulshreshtha, Muhammad Shayan, Robert Belfer, Siva Reddy, Iulian Serban, E. Kochmar

Task-Adaptive Pre-Training for Boosting Learning With Noisy Labels: A Study on Text Classification for African Languages Permalink

D. Zhu, Michael A. Hedderich, Fangzhou Zhai, David Ifeoluwa Adelani, D. Klakow

Question Personalization in an Intelligent Tutoring System Permalink

Sabina Elkins, Robert Belfer, E. Kochmar, Iulian Serban, J. Cheung

MaskEval: Weighted MLM-Based Evaluation for Text Summarization and Simplification Permalink

Yu Lu Liu, Rachel Bawden, Thomas Scaliom, Benoît Sagot, J. Cheung

An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models Permalink

Nicholas Meade, Elinor Poole-Dayan, Siva Reddy

A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation Permalink

David Ifeoluwa Adelani, Jesujoba Oluwadara Alabi, Angela Fan, Julia Kreutzer, Xiaoyu Shen, Machel Reid, Dana Ruiter, D. Klakow, Peter Nabende, Ernie Chang, T...

MCSE: Multimodal Contrastive Learning of Sentence Embeddings Permalink

Miaoran Zhang, Marius Mosbach, David Ifeoluwa Adelani, Michael A. Hedderich, D. Klakow

yosm: A new yoruba sentiment corpus for movie reviews Permalink

Iyanuoluwa Shode, David Ifeoluwa Adelani, Anna Feldman

Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification Permalink

D. Zhu, Michael A. Hedderich, Fangzhou Zhai, David Ifeoluwa Adelani, D. Klakow

Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning Permalink

Jesujoba Oluwadara Alabi, David Ifeoluwa Adelani, Marius Mosbach, D. Klakow

Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment Permalink

Zichao Li, Prakhar Sharma, Xing Han Lu, Jackie C. K. Cheung, Siva Reddy

Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation Permalink

Kushal Arora, Layla El Asri, Hareesh Bahuleyan, J. Cheung

Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation? Permalink

E. Lee, Sarubi Thillainathan, Shravan Nayak, Shravan Nayak, Surangika Ranathunga, David Ifeoluwa Adelani, Ruisi Su, Arya D. McCarthy

IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages Permalink

Emanuele Bugliarello, Fangyu Liu, Jonas Pfeiffer, Siva Reddy, Desmond Elliott, E. Ponti, Ivan Vulic

NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis Permalink

Shamsuddeen Hassan Muhammad, David Ifeoluwa Adelani, I. Ahmad, Idris Abdulmumin, Bello Shehu Bello, M. Choudhury, Chris C. Emezue, Anuoluwapo Aremu, Saheed A...

Does entity abstraction help generative Transformers reason? Permalink

Nicolas Gontier, Siva Reddy, C. Pal

D IALOGUE P IDGIN T EXT A DAPTATION VIA C ON - TRASTIVE F INE -T UNING Permalink

Ernie Chang, Jesujoba Oluwadara Alabi, David Ifeoluwa Adelani, Vera Demberg

Syntactic Substitutability as Unsupervised Dependency Syntax Permalink

Jasper Jian, Siva Reddy

FaithDial: A Faithful Benchmark for Information-Seeking Dialogue Permalink

Nouha Dziri, Ehsan Kamalloo, Sivan Milton, O. Zaiane, Mo Yu, E. Ponti, Siva Reddy

On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models? Permalink

Nouha Dziri, Sivan Milton, Mo Yu, Osmar R Zaiane, Siva Reddy

Image Retrieval from Contextual Descriptions Permalink

Benno Krojer, Vaibhav Adlakha, Vibhav Vineet, Yash Goyal, E. Ponti, Siva Reddy

Evaluating Distributional Distortion in Neural Language Modeling Permalink

Benjamin LeBrun, Alessandro Sordoni, T. O’Donnell

Combining Modular Skills in Multitask Learning Permalink

E. Ponti, Alessandro Sordoni, Siva Reddy

Does entity abstraction help generative Transformers reason? Permalink

Nicolas Gontier, Siva Reddy, C. Pal

Findings of the WMT’22 Shared Task on Large-Scale Machine Translation Evaluation for African Languages Permalink

David Ifeoluwa Adelani, Md Mahfuz Ibn Alam, Antonios Anastasopoulos, Akshita Bhagia, M. Costa-jussà, Jesse Dodge, FAHIM FAISAL, C. Federmann, Natalia Fedorov...

Investigating the Performance of Transformer-Based NLI Models on Presuppositional Inferences Permalink

Jad Kabbara, J. Cheung

Source-summary Entity Aggregation in Abstractive Summarization Permalink

J. González, Annie Louis, J. Cheung

Few-Shot Pidgin Text Adaptation via Contrastive Fine-Tuning Permalink

Ernie Chang, Jesujoba Oluwadara Alabi, David Ifeoluwa Adelani, Vera Demberg

Multilingual Language Model Adaptive Fine-Tuning: A Study on African Languages Permalink

Jesujoba Oluwadara Alabi, David Ifeoluwa Adelani, Marius Mosbach, D. Klakow

Building Together - Towards a Roadmap for African Language Technologies Permalink

Kathleen Siminyu, Jade Z. Abbott, Kólá Túbosún, Aremu Anuoluwapo, Blessing K. Sibanda, Kofi A. Yeboah, David Ifeoluwa Adelani, Masabata Mokgesi-Selinga, Fred...

A Multifaceted Framework to Evaluate Evasion, Content Preservation, and Misattribution in Authorship Obfuscation Techniques Permalink

Malik H. Altakrori, Thomas Scialom, B. Fung, J. Cheung

Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge Permalink

Ian Porada, Alessandro Sordoni, J. Cheung

Preventing Author Profiling through Zero-Shot Multilingual Back-Translation Permalink

David Ifeoluwa Adelani, Miaoran Zhang, Xiaoyu Shen, A. Davody, Thomas Kleinbauer, D. Klakow

Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization Permalink

Mengyao Cao, Yue Dong, J. Cheung

Modeling Event Plausibility with Consistent Conceptual Abstraction Permalink

Ian Porada, Kaheer Suleman, A. Trischler, J. Cheung

Characterizing Idioms: Conventionality and Contingency Permalink

Michaela Socolof, J. Cheung, Michael Wagner, T. O’Donnell

TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion Permalink

Jiapeng Wu, Yishi Xu, Yingxue Zhang, Chen Ma, M. Coates, J. Cheung

AI4D - African Language Program Permalink

Kathleen Siminyu, Godson Kalipe, D. Orlic, Jade Z. Abbott, Vukosi Marivate, Sackey Freshia, Prateek Sibal, B. Neupane, David Ifeoluwa Adelani, Amelia Taylor,...

MasakhaNER: Named Entity Recognition for African Languages Permalink

David Ifeoluwa Adelani, Jade Z. Abbott, Graham Neubig, Daniel D’souza, Julia Kreutzer, Constantine Lignos, Chester Palen-Michel, Happy Buzaaba, Shruti Rijhwa...

The Effect of Domain and Diacritics in Yoruba–English Neural Machine Translation Permalink

David Ifeoluwa Adelani, Dana Ruiter, Jesujoba Oluwadara Alabi, Damilola Adebonojo, Adesina Ayeni, Mofetoluwa Adeyemi, Ayodele Awokoya, C. España-Bonet

Deep Discourse Analysis for Generating Personalized Feedback in Intelligent Tutor Systems Permalink

Matt Grenander, Robert Belfer, E. Kochmar, Iulian Serban, Franccois St-Hilaire, J. Cheung

On-the-Fly Attention Modulation for Neural Generation Permalink

Yue Dong, Chandra Bhagavatula, Ximing Lu, Jena D. Hwang, A. Bosselut, J. Cheung, Yejin Choi

Introduction to the special issue on simplicity in grammar learning Permalink

Roni Katzir, T. O’Donnell, E. Rasin

MENYO-20k: A Multi-domain English-Yorùbá Corpus for Machine Translation and Domain Adaptation Permalink

David Ifeoluwa Adelani, Dana Ruiter, Jesujoba Oluwadara Alabi, Damilola Adebonojo, Adesina Ayeni, Mofetoluwa Adeyemi, Ayodele Awokoya, C. España-Bonet

Inspecting the Factuality of Hallucinated Entities in Abstractive Summarization Permalink

Mengyao Cao, Yue Dong, J. Cheung

On-the-Fly Attention Modularization for Neural Generation Permalink

Yue Dong, Chandra Bhagavatula, Ximing Lu, Jena D. Hwang, Antoine Bosselut, J. Cheung, Yejin Choi

The Topic Confusion Task: A Novel Scenario for Authorship Attribution Permalink

Malik H. Altakrori, J. Cheung, B. Fung

Systematic Generalization with Edge Transformers Permalink

Leon Bergen, T. O’Donnell, Dzmitry Bahdanau

The Power of Prompt Tuning for Low-Resource Semantic Parsing Permalink

Nathan Schucher, Siva Reddy, Harm de Vries

Compositional Generalization in Dependency Parsing Permalink

Emily Goodwin, Siva Reddy, T. O’Donnell, Dzmitry Bahdanau

TopiOCQA: Open-domain Conversational Question Answering with Topic Switching Permalink

Vaibhav Adlakha, S. Dhuliawala, Kaheer Suleman, Harm de Vries, Siva Reddy

Visually Grounded Reasoning across Languages and Cultures Permalink

Fangyu Liu, Emanuele Bugliarello, E. Ponti, Siva Reddy, N. Collier, Desmond Elliott

Modelling Latent Translations for Cross-Lingual Transfer Permalink

E. Ponti, Julia Kreutzer, Ivan Vulic, Siva Reddy

End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering Permalink

Devendra Singh Sachan, Siva Reddy, William Hamilton, Chris Dyer, Dani Yogatama

Minimax and Neyman–Pearson Meta-Learning for Outlier Languages Permalink

E. Ponti, Rahul Aralikatte, Disha Shrivastava, Siva Reddy, Anders Søgaard

Understanding by Understanding Not: Modeling Negation in Language Models Permalink

Arian Hosseini, Siva Reddy, Dzmitry Bahdanau, R. Devon Hjelm, Alessandro Sordoni, Aaron Courville

Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval Permalink

Devang Kulshreshtha, Robert Belfer, Iulian Serban, Siva Reddy

Linguistic Dependencies and Statistical Dependence Permalink

Jacob Louis Hoover, Alessandro Sordoni, Wenyu Du, T. O’Donnell

Characterizing Idioms: Conventionality and Contingency Permalink

Michaela Socolof, J. C. Cheung, Michael Wagner, T. O’Donnell

The Topic Confusion Task: A Novel Scenario for Authorship Attribution Permalink

Malik H. Altakrori, Jackie Cheung, Benjamin Fung

Jointly Learning Truth-Conditional Denotations and Groundings using Parallel Attention Permalink

Leon Bergen, Dzmitry Bahdanau, T. O’Donnell

Abg-CoQA: Clarifying Ambiguity in Conversational Question Answering Permalink

M. Guo, Mingda Zhang, Siva Reddy, Malihe Alikhani

The Topic Confusion Task: A Novel Evaluation Scenario for Authorship Attribution Permalink

Malik H. Altakrori, J. C. Cheung, B. Fung

Textual Time Travel: A Temporally Informed Approach to Theory of Mind Permalink

Akshatha Arodi, J. Cheung

Post-Editing Extractive Summaries by Definiteness Prediction Permalink

Jad Kabbara, J. Cheung

Mind the Context: The Impact of Contextualization in Neural Module Networks for Grounding Visual Referring Expressions Permalink

Arjun Reddy Akula, Spandana Gella, Keze Wang, Song-Chun Zhu, Siva Reddy

Discourse-Aware Unsupervised Summarization for Long Scientific Documents Permalink

Yue Dong, Andrei Mircea, J. Cheung

ADEPT: An Adjective-Dependent Plausibility Task Permalink

Ali Emami, Ian Porada, Alexandra Olteanu, Kaheer Suleman, A. Trischler, J. Cheung

Optimizing Deeper Transformers on Small Datasets Permalink

Peng Xu, Dhruv Kumar, Wei Yang, Wenjie Zi, Keyi Tang, Chenyang Huang, J. Cheung, S. Prince, Yanshuai Cao

On the Systematicity of Probing Contextualized Word Representations: The Case of Hypernymy in BERT Permalink

Abhilasha Ravichander, E. Hovy, Kaheer Suleman, A. Trischler, J. Cheung

MENYO-20k: A Multi-domain English - Yorùbá Corpus for Machine Translation Permalink

David Ifeoluwa Adelani, Jesujoba Oluwadara Alabi, Damilola Adebonojo, Adesina Ayeni, Mofetoluwa Adeyemi, Ayodele Awokoya

On Posterior Collapse and Encoder Feature Dispersion in Sequence VAEs Permalink

Teng Long, Yanshuai Cao, J. Cheung

An Analysis of Dataset Overlap on Winograd-Style Tasks Permalink

Ali Emami, A. Trischler, Kaheer Suleman, J. Cheung

Learning Efficient Task-Specific Meta-Embeddings with Word Prisms Permalink

Jingyi He, Kc Tsiolis, Kian Kenyon-Dean, J. Cheung

MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining Permalink

Zhi Wen, Xing Han Lu, Siva Reddy

Deconstructing Word Embedding Algorithms Permalink

Kian Kenyon-Dean, Edward Newell, J. Cheung

TESA: A Task in Entity Semantic Aggregation for Abstractive Summarization Permalink

Clément Jumel, Annie Louis, J. Cheung

Factual Error Correction for Abstractive Summarization Models Permalink

Mengyao Cao, Yue Dong, Jiapeng Wu, J. Cheung

TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion Permalink

Jiapeng Wu, Mengyao Cao, J. Cheung, William L. Hamilton

Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages Permalink

Michael A. Hedderich, David Ifeoluwa Adelani, D. Zhu, Jesujoba Oluwadara Alabi, Udia Markus, D. Klakow

Multi-Fact Correction in Abstractive Text Summarization Permalink

Yue Dong, Shuohang Wang, Zhe Gan, Yu Cheng, J. Cheung, Jingjing Liu

Investigating the Impact of Pre-trained Word Embeddings on Memorization in Neural Networks Permalink

A. Thomas, David Ifeoluwa Adelani, A. Davody, Aditya Mogadala, D. Klakow

Estimating community feedback effect on topic choice in social media with predictive modeling Permalink

David Ifeoluwa Adelani, Ryota Kobayashi, Ingmar Weber, Przemyslaw A. Grabowicz

Privacy Guarantees for De-identifying Text Transformations Permalink

David Ifeoluwa Adelani, A. Davody, Thomas Kleinbauer, D. Klakow

StereoSet: Measuring stereotypical bias in pretrained language models Permalink

Moin Nadeem, Anna Bethke, Siva Reddy

Robust Differentially Private Training of Deep Neural Networks Permalink

A. Davody, David Ifeoluwa Adelani, Thomas Kleinbauer, D. Klakow

On the effect of normalization layers on Differentially Private training of deep Neural networks Permalink

A. Davody, David Ifeoluwa Adelani, Thomas Kleinbauer, D. Klakow

Learning Lexical Subspaces in a Distributional Vector Space Permalink

Kushal Arora, Aishik Chakraborty, J. Cheung

HipoRank: Incorporating Hierarchical and Positional Information into Graph-based Unsupervised Long Document Extractive Summarization Permalink

Yue Dong, Andrei Mircea, J. Cheung

Improving Yor`ub'a Diacritic Restoration Permalink

Iroro Orife, David Ifeoluwa Adelani, Timi E. Fasubaa, Victor Williamson, W. Oyewusi, Olamilekan Wahab, Kólá Túbosún

Distant Supervision and Noisy Label Learning for Low Resource Named Entity Recognition: A Study on Hausa and Yorùbá Permalink

David Ifeoluwa Adelani, Michael A. Hedderich, D. Zhu, Esther van den Berg, D. Klakow

Unsupervised Pidgin Text Generation By Pivoting English Data and Self-Training Permalink

Ernie Chang, David Ifeoluwa Adelani, Xiaoyu Shen, Vera Demberg

Investigating the Influence of Selected Linguistic Features on Authorship Attribution using German News Articles Permalink

Manuel Sage, Pietro Cruciata, Raed Abdo, J. Cheung, Y. Zhao

Storage and Computation of Multimorphemic Words in Turkish Permalink

Rabia Ergin, Emily Morgan, T. O’Donnell

Improving Yorùbá Diacritic Restoration Permalink

Iroro Orife, David Ifeoluwa Adelani, Timi E. Fasubaa, Victor Williamson, W. Oyewusi, Olamilekan Wahab, Kólá Túbosún

Optimizing Deeper Transformers on Small Datasets: An Application on Text-to-SQL Semantic Parsing Permalink

Peng Xu, Wei Yang, Wenjie Zi, Keyi Tang, Chengyang Huang, J. Cheung, Yanshuai Cao

Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle Permalink

Yikang Shen, Shawn Tan, Alessandro Sordoni, Siva Reddy, Aaron Courville

Learning Improvised Chatbots from Adversarial Modifications of Natural Language Feedback Permalink

Makesh Narsimhan Sreedhar, Kun Ni, Siva Reddy

Recursive Top-Down Production for Sentence Generation with Latent Trees Permalink

Shawn Tan, Yikang Shen, T. O’Donnell, Alessandro Sordoni, Aaron C. Courville

Measuring Systematic Generalization in Neural Proof Generation with Transformers Permalink

Nicolas Gontier, Koustuv Sinha, Siva Reddy, C. Pal

Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach Permalink

Wenyu Du, Zhouhan Lin, Yikang Shen, T. O’Donnell, Yoshua Bengio, Yue Zhang

Probing Linguistic Systematicity Permalink

Emily Goodwin, Koustuv Sinha, T. O’Donnell

Words Aren’t Enough, Their Order Matters: On the Robustness of Grounding Visual Referring Expressions Permalink

Arjun Reddy Akula, Spandana Gella, Y. Al-Onaizan, Song-Chun Zhu, Siva Reddy

Statistical Evidence for Learnable Lexical Subclasses in Japanese Permalink

T. Morita, T. O’Donnell

Massive vs. Curated Embeddings for Low-Resourced Languages: the Case of Yorùbá and Twi Permalink

Jesujoba Oluwadara Alabi, Kwabena Amponsah-Kaakyire, David Ifeoluwa Adelani, C. España-Bonet

Deconstructing and reconstructing word embedding algorithms Permalink

Edward Newell, Kian Kenyon-Dean, J. Cheung

Can a Gorilla Ride a Camel? Learning Semantic Plausibility from Text Permalink

Ian Porada, Kaheer Suleman, J. Cheung

Preventing Posterior Collapse in Sequence VAEs with Pooling Permalink

Teng Long, Yanshuai Cao, J. Cheung

Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses Permalink

Matt Grenander, Yue Dong, J. Cheung, Annie Louis

Referring Expression Generation Using Entity Profiles Permalink

Mengyao Cao, J. Cheung

Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Models and Their Human- and Machine-based Detection Permalink

David Ifeoluwa Adelani, H. Mai, Fuming Fang, H. Nguyen, J. Yamagishi, I. Echizen

Generating Character Descriptions for Automatic Summarization of Fiction Permalink

Weiwei Zhang, J. Cheung, J. Oren

Learning Multi-Task Communication with Message Passing for Sequence Learning Permalink

Pengfei Liu, Jie Fu, Yue Dong, Xipeng Qiu, J. Cheung

EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing Permalink

Yue Dong, Zichao Li, Mehdi Rezagholizadeh, J. Cheung

Understanding the Behaviour of Neural Abstractive Summarizers using Contrastive Examples Permalink

Krtin Kumar, J. Cheung

On Variational Learning of Controllable Representations for Text without Supervision Permalink

Peng Xu, J. Cheung, Yanshuai Cao

Unsupervised Controllable Text Generation with Global Variation Discovery and Disentanglement Permalink

Peng Xu, Yanshuai Cao, J. Cheung

A Cross-Domain Transferable Neural Coherence Model Permalink

Peng Xu, H. Saghir, Jin Sung Kang, Teng Long, A. Bose, Yanshuai Cao, J. Cheung

Demographic Inference and Representative Population Estimates from Multilingual Social Media Data Permalink

Zijian Wang, Scott A. Hale, David Ifeoluwa Adelani, Przemyslaw A. Grabowicz, Timo Hartmann, Fabian Flöck, David Jurgens

What comes next? Extractive summarization by next-sentence prediction Permalink

Jingyun Liu, J. Cheung, Annie Louis

Learning Multi-Task Communication with Message Passing Permalink

Peng Liu, Jie Fu, Yue Dong, Xipeng Qiu, J. Cheung

Evaluating systematicity in neural networks with natural language inference Permalink

Emily Goodwin, Koustuv Sinha, T. O’Donnell

Universality and diversity in human song Permalink

Samuel A. Mehr, Manvir Singh, D. Knox, Daniel M. Ketter, Daniel Pickens-Jones, S. Atwood, Christopher Lucas, Nori Jacoby, Alena Egner, Erin J. Hopkins, Rhea ...

Five Ways in Which Computational Modeling Can Help Advance Cognitive Science: Lessons From Artificial Grammar Learning Permalink

Willem H. Zuidema, R. French, Raquel G. Alhama, Kevin Ellis, T. O’Donnell, Tim Sainburg, T. Gentner

Clustering-Oriented Representation Learning with Attractive-Repulsive Loss Permalink

Kian Kenyon-Dean, Andre Cianflone, Lucas Page-Caccia, Guillaume Rabusseau, J. Cheung, Doina Precup

Multi-task Learning over Graph Structures Permalink

Pengfei Liu, Jie Fu, Yue Dong, Xipeng Qiu, J. Cheung

Contextualized Non-local Neural Networks for Sequence Learning Permalink

Pengfei Liu, Shuaichen Chang, Xuanjing Huang, Jian Tang, J. Cheung

On the Evaluation of Common-Sense Reasoning in Natural Language Understanding Permalink

P. Trichelair, Ali Emami, J. Cheung, A. Trischler, Kaheer Suleman, Fernando Diaz

How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG Permalink

P. Trichelair, Ali Emami, A. Trischler, Kaheer Suleman, J. Cheung

The Hard-CoRe Coreference Corpus: Removing Gender and Number Cues for Difficult Pronominal Anaphora Resolution Permalink

Ali Emami, P. Trichelair, A. Trischler, Kaheer Suleman, Hannes Schulz, J. Cheung

The KnowRef Coreference Corpus: Removing Gender and Number Cues for Difficult Pronominal Anaphora Resolution Permalink

Ali Emami, P. Trichelair, A. Trischler, Kaheer Suleman, Hannes Schulz, J. Cheung

A Knowledge Hunting Framework for Common Sense Reasoning Permalink

Ali Emami, Noelia De La Cruz, A. Trischler, Kaheer Suleman, J. Cheung

BanditSum: Extractive Summarization as a Contextual Bandit Permalink

Yue Dong, Yikang Shen, Eric Crawford, H. V. Hoof, J. Cheung

Let’s do it “again”: A First Computational Approach to Detecting Adverbial Presupposition Triggers Permalink

Andre Cianflone, Yulan Feng, Jad Kabbara, J. Cheung

Coarse Lexical Frame Acquisition at the Syntax–Semantics Interface Using a Latent-Variable PCFG Model Permalink

Laura Kallmeyer, B. Zadeh, J. Cheung

A Generalized Knowledge Hunting Framework for the Winograd Schema Challenge Permalink

Ali Emami, A. Trischler, Kaheer Suleman, J. Cheung

Resolving Event Coreference with Supervised Representation Learning and Clustering-Oriented Regularization Permalink

Kian Kenyon-Dean, J. Cheung, Doina Precup

Constructing a Lexicon of Relational Nouns Permalink

Edward Newell, J. Cheung

Commonsense mining as knowledge base completion? A study on the impact of novelty Permalink

Stanislaw Jastrzebski, Dzmitry Bahdanau, Seyedarian Hosseini, Michael Noukhovitch, Yoshua Bengio, J. Cheung

Building a Neural Semantic Parser from a Domain Ontology Permalink

Jianpeng Cheng, Siva Reddy, Mirella Lapata

CoQA: A Conversational Question Answering Challenge Permalink

Siva Reddy, Danqi Chen, Christopher D. Manning

Universality and diversity in human song Permalink

Samuel A. Mehr, Manvir Singh, D. Knox, Daniel M. Ketter, Daniel Pickens-Jones, S. Atwood, Christophe Lucas, Nori Jacoby, Alena Egner, Erin J. Hopkins, Rhea M...

A Hierarchical Neural Attention-based Text Classifier Permalink

Koustuv Sinha, Yue Dong, J. Cheung, D. Ruths

The evolutionary causes of irregularity: Evidence for an irregularization bias in morphological learning Permalink

T. O’Donnell, Kenny Smith

Learning Typed Entailment Graphs with Global Soft Constraints Permalink

Mohammad Javad Hosseini, Nathanael Chambers, Siva Reddy, Xavier R. Holt, Shay B. Cohen, Mark Johnson, Mark Steedman

Arabic Authorship Attribution Permalink

Malik H. Altakrori, F. Iqbal, B. Fung, Steven H. H. Ding, A. Tubaishat

World Knowledge for Reading Comprehension: Rare Entity Prediction with Hierarchical LSTMs Using External Descriptions Permalink

Teng Long, Emmanuel Bengio, Ryan Lowe, J. Cheung, Doina Precup

Predicting Success in Goal-Driven Human-Human Dialogues Permalink

Michael Noseworthy, J. Cheung, Joelle Pineau

Detecting Large Concept Extensions for Conceptual Analysis Permalink

L. Chartrand, J. Cheung, M. Bouguessa

Nifty Assignments Permalink

Nick Parlante, Julie Zelenski, Dave Feinberg, Kunal Mishra, Josh Hug, Kevin Wayne, Michael Guerzhoy, J. Cheung, François Pitt

Universal Dependencies 2.0 – CoNLL 2017 Shared Task Development and Test Data Permalink

Joakim Nivre, Zeljko Agic, Lars Ahrenberg, Lene Antonsen, M. J. Aranzabe, Masayuki Asahara, Luma Ateyah, Mohammed Attia, Aitziber Atutxa, E. Badmaeva, Miguel...

Grammar Induction for Minimalist Grammars using Variational Bayesian Inference : A Technical Report Permalink

Eva Portelance, Amelia Bruno, Daniel Harasim, Leon Bergen, T. O’Donnell

Computer-Assisted Conceptual Analysis of Textual Data as Applied to Philosophical Corpuses Permalink

J. Meunier, L. Chartrand, J. Cheung, Mathieu Valette, M. Bayle

Formalizing accessibility using linguistic productivity Permalink

Kyle Mahowald, J. Tenenbaum, T. O’Donnell

Syntax-aware Neural Machine Translation Using CCG Permalink

Maria Nadejde, Siva Reddy, Rico Sennrich, Tomasz Dwojak, Marcin Junczys-Dowmunt, Philipp Koehn, Alexandra Birch

Learning an Executable Neural Semantic Parser Permalink

Jianpeng Cheng, Siva Reddy, V. Saraswat, Mirella Lapata

Learning to Paraphrase for Question Answering Permalink

Li Dong, Jonathan Mallinson, Siva Reddy, Mirella Lapata

Learning Structured Natural Language Representations for Semantic Parsing Permalink

Jianpeng Cheng, Siva Reddy, V. Saraswat, Mirella Lapata

Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks Permalink

R. Das, M. Zaheer, Siva Reddy, A. McCallum

Universal Dependencies to Logical Form with Negation Scope Permalink

Federico Fancellu, Siva Reddy, Adam Lopez, B. Webber

Universal Semantic Parsing Permalink

Siva Reddy, Oscar Täckström, Slav Petrov, Mark Steedman, Mirella Lapata

Predicting Target Language CCG Supertags Improves Neural Machine Translation Permalink

Maria Nadejde, Siva Reddy, Rico Sennrich, Tomasz Dwojak, Marcin Junczys-Dowmunt, Philipp Koehn, Alexandra Birch

CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies Permalink

Daniel Zeman, M. Popel, Milan Straka, Jan Hajic, Joakim Nivre, Filip Ginter, Juhani Luotolahti, Sampo Pyysalo, Slav Petrov, Martin Potthast, Francis M. Tyers...

Evaluating Hierarchies of Verb Argument Structure with Hierarchical Clustering Permalink

Jesse Mu, Joshua K. Hartshorne, T. O’Donnell

Enhancing the reusability and interoperability of artificial neural networks with DEVS modeling and simulation Permalink

David Ifeoluwa Adelani, M. Traoré

Unsupervised learning of VerbNet argument structure Permalink

Jesse Mu, T. O’Donnell, Joshua K. Hartshorne

Evaluating Induced CCG Parsers on Grounded Semantic Parsing Permalink

Yonatan Bisk, Siva Reddy, John Blitzer, J. Hockenmaier, Mark Steedman

Question Answering on Freebase via Relation Extraction and Textual Evidence Permalink

Kun Xu, Siva Reddy, Yansong Feng, Songfang Huang, Dongyan Zhao

Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing Permalink

Shashi Narayan, Siva Reddy, Shay B. Cohen

Assessing Relative Sentence Complexity using an Incremental CCG Parser Permalink

Bharat Ram Ambati, Siva Reddy, Mark Steedman

Transforming Dependency Structures to Logical Forms for Semantic Parsing Permalink

Siva Reddy, Oscar Täckström, Michael Collins, T. Kwiatkowski, Dipanjan Das, Mark Steedman, Mirella Lapata

Proceedings of the 6th Workshop on Cognitive Modeling and Computational Linguistics, CMCL@NAACL-HLT 2015, Denver, CO, USA, June 4, 2015 Permalink

T. O’Donnell, Marten van Schijndel

The English Past Tense: Simulations Permalink

T. O’Donnell

English Derivational Morphology: Simulations Permalink

T. O’Donnell

Evaluating Models of Computation and Storage in Human Sentence Processing Permalink

Thang Luong, T. O’Donnell, Noah D. Goodman

A model of rapid phonotactic generalization Permalink

Tal Linzen, T. O’Donnell

The causes and consequences explicit in verbs Permalink

Joshua K. Hartshorne, T. O’Donnell, J. Tenenbaum

A Devs-Based Ann Training and Prediction Platform Permalink

David Ifeoluwa Adelani

UvA-DARE (Digital Academic Repository) A Usage-Based Model of Early Grammatical Development A Usage-Based Model of Early Grammatical Development Permalink

V. Demberg, T. O’Donnell

Large-scale Semantic Parsing without Question-Answer Pairs Permalink

Siva Reddy, Mirella Lapata, Mark Steedman

Social dialect and men’s voice pitch influence women’s mate preferences Permalink

J. O’Connor, Paul J. Fraccaro, K. Pisanski, C. C. Tigue, T. O’Donnell, D. Feinberg

DSS: Text Similarity Using Lexical Alignments of Form, Distributional Semantics and Grammatical Relations Permalink

Diana McCarthy, Spandana Gella, Siva Reddy

Word Sketches for Turkish Permalink

Bharat Ram Ambati, Siva Reddy, A. Kilgarriff

A Secure e-Voting Architecture Permalink

A. Sodiya, S. Onashoga, David Ifeoluwa Adelani

Frozen Chunks and Generalized Representations: The Case of the English Dative Alternation Permalink

E. Conwell, T. O’Donnell, J. Snedeker

Dynamic and Static Prototype Vectors for Semantic Composition Permalink

Siva Reddy, I. Klapaftis, Diana McCarthy, S. Manandhar

An Empirical Study on Compositionality in Compound Nouns Permalink

Siva Reddy, Diana McCarthy, S. Manandhar

Productivity and Reuse in Language Permalink

T. O’Donnell, J. Snedeker, J. Tenenbaum, Noah D. Goodman

Productivity and Reuse in Language: a Developmental Study Permalink

T. O’Donnell, J. Snedeker, J. Tenenbaum, Noah D. Goodman

A Corpus Factory for Many Languages Permalink

A. Kilgarriff, Siva Reddy, Jan Pomikálek, Avinesh P.V.S

Linking meaning to language: linguistic universals and variation Permalink

Joshua K. Hartshorne, T. O’Donnell, Y. Sudo, Miki Uruwashi, J. Snedeker

Fragment Grammars: Exploring Computation and Reuse in Language Permalink

T. O’Donnell, Noah D. Goodman, J. Tenenbaum

Learning English as a Foreign Language in Korea : Does CALL have a place ? Permalink

T. O’Donnell

Beyond the argument from design Permalink

Willem H. Zuidema, T. O’Donnell, A. Cangelosi, Andrew D. M. Smith, Kenny Smith

Proceedings of 3rd Workshop on NLP and XML (NLPXML-2003) Language Technology and the Semantic Web Permalink

J. Carletta, J. Kilgour, T. O’Donnell, S. Evert, Holger Voormann

The NXT Object Model Permalink

S. Evert, J. Carletta, T. O’Donnell, J. Kilgour, Andreas Vögele, Holger Voormann

The NITE Object Model Library for Handling Structured Linguistic Annotation on Multimodal Data Sets Permalink

J. Carletta, J. Kilgour, T. O’Donnell, S. Evert, Holger Voormann

Robust Reward Modeling via Causal Rubrics

Harman Singh

Rethinking Sorting in LLM-Based Pairwise Ranking with Batching and Caching

Juan Wisznia

Implicit Chain-of-Thought: Internalizing Reasoning in Language Models

Yuntian Deng

Towards Robust Detection of AI-generated Text: Sampling Pitfalls and Ensemble Resilience

Matthieu Dubois

Measuring Word Meaning Change Across Time and Speaker Age

Gaurav Kamath

Compositional Reasoning for Natural Language Comprehension and Grounding Leveraging Neuro-Symbolic AI

Parisa Kordjamshidi

XHAILe: Explainable Hybrid AI for Computational Law and Accurate Legal Chatbots

Thomas Hildebrandt

Memorisation meets compositionality in natural language processing

Verna Dankers

Data Curation, Curriculum, and Cascade Serving for Better Small Language Models

Wanru Zhao

(RSA)²: A Rhetorical-Strategy-Aware Rational Speech Act Framework for Figurative Language Understanding

Cesare Spinoso-di Piano

Using Shapley interactions to understand how models use structure

Diganta Misra

LitLLMs, LLMs for Literature Review: Are we there yet?

Gaurav Sahu

Large language models, large culture models? The role of language in the cultural values exhibited by LLMs

Ayla Rigouts Terryn

Epistemic Injustice in the Age of Language Models

Angelie Kraft

LLMs and Language Grounding

Reto Gubelmann and Stevan Harnad

Summer 2024

For the Summer 2025 semester, the reading group will meet on Fridays at 1PM. Meetings will be held in a hybrid fashion. More information including room locat...

Perceptions of Linguistic Uncertainty by Language Models and Humans

Catarina Belem

A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical Alignment

Jean-Philippe Corbeil

RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework

Yifan Wang

NLP Rountable: DeepSeek

Sara Vera Marjanovic

AI Conversationalists know what to say but not when to speak

Muhammad Umair

LLMs/VLMs with Nonparametric Memory: Experiments on Query Generation and Visual Question Answering

Amal Zouaq

NLP Roundtable: The Reviewing Process

Rountable discussion

NLP Roundtable: Where have we been and where are we going?

Rountable discussion

Winter 2025

For the Winter 2025 semester, the reading group will meet every other week on Fridays at 1PM (with some exceptions to be expected). Meetings will be held in ...

Towards Principled Model Evaluation Under Imperfect “Ground Truth” Labels

Luke Guerdan

Distilling an End-to-End Voice Assistant Without Instruction Training Data

William Held

Towards a Generalist Web Agent

Boyuan Zheng

Applications and Enhancements of LLM Agents Across Diverse Environments

Bang Liu

Reframing linguistic bootstrapping as joint inference using visually-grounded grammar induction models

Eva Portelance

Efficient Model Development in the Era of Large Language Models

Tu Vu

Intern Presentations

Steven Koniaev, Nathan Zeweniuk

Intern Presentations

Fabian David Schmidt, Ada Tur

Intriguing properties of generative classifiers: generative models align with human visual perception for object recognition

Priyank Jaini

Fall 2024

For the Fall 2024 semester, the reading group will meet on Fridays at 11:30AM (with some exceptions to be expected). Meetings will be held in a hybrid fashio...

Implicit Discourse Relation Recognition

Nelson Filipe Costa

Balancing between Efficiencies, Modularity, and Performance of (L)LMs

Prof. Ivan Vulić

Cross-Modality Safety Alignment in Multi-Modal LLMs

Erfan Shayegani

Stacking your transformers: A closer look at model growth for efficient LLM pre-training

Wenyu Du

Self-Alignment of Large Language Models

Jason Weston

Are LLMs Reasoning, Repeating or Just Biased? A Case Study with English Pronouns

Vagrant Gautam

Squirrel or Skunk? NLP Models Face the Long Tail of Language

Prof. Nathan Schneider

Representation-level information aggregation in LLMs

Yu Bai

The Role of Analysis Work in NLP

Marius Mosbach

Inductive Biases and Concept-based Explainability

Matthias Lindermann and Fanny Jourdan

LLMs as Text Encoders

Vaibhav Adlakha

Digital Agents and VLMs

Tianbao Xie and Danyang Zhang

High-Quality Human Evaluation of Generated Texts

Ehud Reiter

From Summarization Evaluation to Digital Agents

Ori Ernst and Xing Han Lù

Summer 2024

For the Summer 2024 semester, the reading group will meet every other Monday starting April 22nd at 11AM (with some exceptions to be expected). Meetings will...

Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference

Piotr Nawrot

Multi-Teacher Distillation: An Ensemble-Then-Distill Approach

Prof. Lili Mou

Natural Language Understanding with Deep Learning / Computational Semantics

Course Code: COMP 545 & LING 545 (Fall 2025) Instructors: Siva Reddy (office hours: Tuesday 3pm, ENGMC 104N) and Marius Mosbach Teaching Assistant...

Evaluation of Natural Language Processing Systems

Course codes: COMP 766 Section 002(Winter 2025) Instructors: Jackie Chi Kit Cheung[office hours: Wednesdays, 15:00pm – 15:50pm in McConnell 1...

Multilingual Representation Learning

Course code: COMP 598 002(Winter 2025) Instructors: David I. Adelani Classroom: McConnell Engineering Building 103 Time: Tuesdays...

From Natural Language to Data Science

Course codes: COMP 345 & LING 345 (Winter 2025) Instructors: Siva Reddy[office hours: Thursdays 1:00pm–2:00pm ENGMC 104N (immediately aft...

Large Language Models

Course codes: COMP 767 & LING 782 (Fall 2024) Instructors: Siva Reddy Classroom: WONG 1050 Time: Tuesdays and Thursdays, 11:35 am – 12:55 pm L...

From Natural Language to Data Science

Course codes: COMP 345 & LING 345 (Winter 2024) Instructors: Siva Reddy[office hours: Tuesdays 3pm ENGMC 104N], Morgan Sonderegger Teaching Assist...

Formal and Neural Models of Pragmatics

Course codes: COMP 767 (Winter 2024) Instructors: Jackie Cheung Classroom: Burnside 719A Time: Tuesdays and Thursdays, 11:35 am - 12:55 pm Links: ...

Natural Language Understanding with Deep Learning / Computational Semantics

Course Code: COMP 545 & LING 484/782 (Winter 2024) Instructor: Siva Reddy (office hours: Tuesday 3pm, ENGMC 104N) Teaching Assistants: Aristides M...

Natural Language Processing

Course codes: COMP 550 (Fall 2023) Instructors: Jackie Cheung Course website: Administered through Ed and myCourses

Natural Language Understanding with Deep Learning / Computational Semantics

Course Code: COMP 599 & LING 484/782 (Fall 2022) Instructor: Siva Reddy (office hours: Tuesday 12:00pm–12:45pm and 2:15pm–3:00pm, ENGMC 104N) Teac...

Natural Language Understanding with Deep Learning / Computational Semantics

From Natural Language to Data Science

Natural Language Processing

Course codes: COMP 550 Instructors: Jackie Cheung Course website: Administered through Ed and myCourses

Natural Language Processing

Course codes: COMP 550 Instructors: Jackie Cheung Course website: here

Natural Language Processing

Course codes: COMP 550 Instructors: Jackie Cheung Course website: here

Natural Language Processing

Course codes: COMP 550 Instructors: Jackie Cheung Course website: here

Natural Language Processing

Course codes: COMP 550 Instructors: Jackie Cheung Course website: here

Introduction to Natural Language Processing

Course codes: COMP 550 Instructors: Jackie Cheung Course website: here

Introduction to Natural Language Processing

Course codes: COMP 550 Instructors: Jackie Cheung Course website: here

Implicit Discourse Relation Recognition

Nelson Filipe Costa

Balancing between Efficiencies, Modularity, and Performance of (L)LMs

Prof. Ivan Vulić

Cross-Modality Safety Alignment in Multi-Modal LLMs

Erfan Shayegani

Stacking your transformers: A closer look at model growth for efficient LLM pre-training

Wenyu Du

Self-Alignment of Large Language Models

Jason Weston

Are LLMs Reasoning, Repeating or Just Biased? A Case Study with English Pronouns

Vagrant Gautam

Squirrel or Skunk? NLP Models Face the Long Tail of Language

Prof. Nathan Schneider

Representation-level information aggregation in LLMs

Yu Bai

The Role of Analysis Work in NLP

Marius Mosbach

Inductive Biases and Concept-based Explainability

Matthias Lindermann and Fanny Jourdan

LLMs as Text Encoders

Vaibhav Adlakha

Digital Agents and VLMs

Tianbao Xie and Danyang Zhang

High-Quality Human Evaluation of Generated Texts

Ehud Reiter

From Summarization Evaluation to Digital Agents

Ori Ernst and Xing Han Lù

Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference

Piotr Nawrot

Multi-Teacher Distillation: An Ensemble-Then-Distill Approach

Prof. Lili Mou

Large language models, large culture models? The role of language in the cultural values exhibited by LLMs

Ayla Rigouts Terryn

Epistemic Injustice in the Age of Language Models

Angelie Kraft

LLMs and Language Grounding

Reto Gubelmann and Stevan Harnad

Perceptions of Linguistic Uncertainty by Language Models and Humans

Catarina Belem

A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical Alignment

Jean-Philippe Corbeil

RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework

Yifan Wang

NLP Rountable: DeepSeek

Sara Vera Marjanovic

AI Conversationalists know what to say but not when to speak

Muhammad Umair

LLMs/VLMs with Nonparametric Memory: Experiments on Query Generation and Visual Question Answering

Amal Zouaq

NLP Roundtable: The Reviewing Process

Rountable discussion

NLP Roundtable: Where have we been and where are we going?

Rountable discussion

Towards Principled Model Evaluation Under Imperfect “Ground Truth” Labels

Luke Guerdan

Distilling an End-to-End Voice Assistant Without Instruction Training Data

William Held

Towards a Generalist Web Agent

Boyuan Zheng

Applications and Enhancements of LLM Agents Across Diverse Environments

Bang Liu

Reframing linguistic bootstrapping as joint inference using visually-grounded grammar induction models

Eva Portelance

Efficient Model Development in the Era of Large Language Models

Tu Vu

Intern Presentations

Steven Koniaev, Nathan Zeweniuk

Intern Presentations

Fabian David Schmidt, Ada Tur

Intriguing properties of generative classifiers: generative models align with human visual perception for object recognition

Priyank Jaini

XHAILe: Explainable Hybrid AI for Computational Law and Accurate Legal Chatbots

Thomas Hildebrandt

Memorisation meets compositionality in natural language processing

Verna Dankers

Data Curation, Curriculum, and Cascade Serving for Better Small Language Models

Wanru Zhao

(RSA)²: A Rhetorical-Strategy-Aware Rational Speech Act Framework for Figurative Language Understanding

Cesare Spinoso-di Piano

Using Shapley interactions to understand how models use structure

Diganta Misra

LitLLMs, LLMs for Literature Review: Are we there yet?

Gaurav Sahu

Robust Reward Modeling via Causal Rubrics

Harman Singh

Rethinking Sorting in LLM-Based Pairwise Ranking with Batching and Caching

Juan Wisznia

Implicit Chain-of-Thought: Internalizing Reasoning in Language Models

Yuntian Deng

Towards Robust Detection of AI-generated Text: Sampling Pitfalls and Ensemble Resilience

Matthieu Dubois

Measuring Word Meaning Change Across Time and Speaker Age

Gaurav Kamath

Compositional Reasoning for Natural Language Comprehension and Grounding Leveraging Neuro-Symbolic AI

Parisa Kordjamshidi

Summer 2024

For the Summer 2025 semester, the reading group will meet on Fridays at 1PM. Meetings will be held in a hybrid fashion. More information including room locat...

Winter 2025

For the Winter 2025 semester, the reading group will meet every other week on Fridays at 1PM (with some exceptions to be expected). Meetings will be held in ...

Fall 2024

For the Fall 2024 semester, the reading group will meet on Fridays at 11:30AM (with some exceptions to be expected). Meetings will be held in a hybrid fashio...

Summer 2024

For the Summer 2024 semester, the reading group will meet every other Monday starting April 22nd at 11AM (with some exceptions to be expected). Meetings will...