CLNov 29, 2022
End-to-End Neural Discourse Deixis Resolution in Dialogue
arXiv:2211.15980v2290 citationsh-index: 7
Originality Synthesis-oriented
AI Analysis
This work addresses the problem of resolving discourse deixis in dialogue for natural language processing applications, but it is incremental as it builds on prior methods.
The paper tackled discourse deixis resolution in dialogue by adapting an existing span-based entity coreference model with task-specific extensions, achieving state-of-the-art results on the CODI-CRAC 2021 shared task datasets.
We adapt Lee et al.'s (2018) span-based entity coreference model to the task of end-to-end discourse deixis resolution in dialogue, specifically by proposing extensions to their model that exploit task-specific characteristics. The resulting model, dd-utt, achieves state-of-the-art results on the four datasets in the CODI-CRAC 2021 shared task.