Enhancing Long-Distance Dialogue History Modeling for Better Dialogue Ellipsis and Coreference Resolution

Autor:	Fang Kong, Zixin Ni
Rok vydání:	2021
Předmět:	Coreference Computer science business.industry Ellipsis (linguistics) Artificial intelligence Resolution (logic) computer.software_genre business computer Encoder Single sequence Natural language processing Task (project management)
Zdroj:	Natural Language Processing and Chinese Computing ISBN: 9783030884796 NLPCC (1)
Popis:	Previous work on dialogue-specific ellipsis and coreference resolution usually concatenates all dialogue history utterances into a single sequence. It may mislead the model to attend to inappropriate parts and to copy from wrong utterances when the dialogue history is long. In this paper, we aim to model dialogue history from multiple granularities and take a deep look into the semantic connection between the dialogue history and the omitted or coreferred expressions. To achieve this, we propose a speaker highlight dialogue history encoder and a top-down hierarchical copy mechanism to generate the complete utterances. We conduct dozens of experiments on the CamRest676 dataset, and the experimental results show that our methods are expert in long-distance dialogue history modeling and can significantly improve the performance of ellipsis and coreference resolution in the dialogue task.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::5ccd4e9a566a47f1a7d10b2308d42306 https://doi.org/10.1007/978-3-030-88480-2_38 Zobrazit plný text záznamu