Implicit Discourse Relation Recognition

Nelson Filipe Costa

Concordia University

The NLP Reading Group is happy to receive Nelson Filipe Costa who will be giving a talk in-person on “Implicit Discourse Relation Recognition”.

Talk Description

In this presentation, we address the inherent ambiguity in Implicit Discourse Relation Recognition (IDRR) by introducing a novel multi-task classification model capable of learning both multi-label and single-label representations of discourse relations. Leveraging the DiscoGeM corpus, we train and evaluate our model on both multi-label and traditional single-label classification tasks. To the best of our knowledge, our work presents the first truly multi-label classifier in IDRR, establishing a benchmark for multi-label classification and achieving SOTA results in single-label classification on DiscoGeM. Additionally, we evaluate our model on the PDTB 3.0 corpus for single-label classification without any prior exposure to its data. While the performance is below the current SOTA, our model demonstrates promising results indicating potential for effective transfer learning across both corpora.

Speaker Bio

Nelson is a PhD student at the Computational Linguistics lab (CLaC) at Concordia University under the supervision of Professor Leila Kosseim.

Logistics

Date: August 26th
Time: 11:00AM
Location: F01 or via Zoom (See email)