Best Paper Award at SIGDIAL for Dr. Carenini

Dr. Giuseppe Carenini and fellow authors Chuyuan Li and Yuwei Yin have won a Best Paper Award at the 25th SIGDlAL (Special Interest Group on Discourse and Dialogue) in Kyoto Japan.

The abstract for their award-winning paper "Dialogue Discourse Parsing as Generation: a Sequence-to-Sequence LLM-based Approach" is as follows:

"Existing works on dialogue discourse parsing mostly utilize encoder-only models and sophisticated decoding strategies to extract structures. Despite recent advances in Large Language Models (LLMs), there has been little work applying directly these models on discourse parsing. To fully utilize the rich semantic and discourse knowledge in LLMs, we explore the feasibility of transforming discourse parsing into a generation task using a text-to-text paradigm. Our approach is intuitive and requires no modification of the LLM architecture. Experimental results on STAC and Molweni datasets show that a sequence-to-sequence model such as T0 can perform reasonably well. Notably, our improved transition-based sequence-to-sequence system achieves new state-of-the-art performance on Molweni, demonstrating the effectiveness of the proposed method. Furthermore, our systems can generate richer discourse structures such as directed acyclic graphs, whereas previous methods are limited to trees."

Chuyuan Li is a postdoc fellow and Yuwei Yin is a graduate student working under the supervision of Dr. Carenini in the Natural Language Processing Group (NLP) at UBC Computer Science.