Zero-shot cross-lingual conversational semantic role labeling

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with host publication)peer-review

1 Scopus Citations
View graph of relations

Detail(s)

Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics
Subtitle of host publicationNAACL 2022
EditorsMarine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
PublisherAssociation for Computational Linguistics
Pages269-281
ISBN (Print)9781955917766
Publication statusPublished - Jul 2022

Publication series

NameFindings of the Association for Computational Linguistics: NAACL - Findings

Conference

Title2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022)
LocationHyatt Regency Seattle + Online
PlaceUnited States
CityWashington
Period10 - 15 July 2022

Link(s)

Abstract

While conversational semantic role labeling (CSRL) has shown its usefulness on Chinese conversational tasks, it is still under-explored in non-Chinese languages due to the lack of multilingual CSRL annotations for the parser training. To avoid expensive data collection and error-propagation of translation-based methods, we present a simple but effective approach to perform zero-shot cross-lingual CSRL.Our model implicitly learns language-agnostic, conversational structure-aware and semantically rich representations with the hierarchical encoders and elaborately designed pre-training objectives. Experimental results show that our model outperforms all baselines by large margins on two newly collected English CSRL test sets. More importantly, we confirm the usefulness of CSRL to non-Chinese conversational tasks such as the question-in-context rewriting task in English and the multi-turn dialogue response generation tasks in English, German and Japanese by incorporating the CSRL information into the downstream conversation-based models. We believe this finding is significant and will facilitate the research of non-Chinese dialogue tasks which suffer the problems of ellipsis and anaphora.

Research Area(s)

Citation Format(s)

Zero-shot cross-lingual conversational semantic role labeling. / Wu, Han; Tan, Haochen; Xu, Kun et al.
Findings of the Association for Computational Linguistics: NAACL 2022. ed. / Marine Carpuat; Marie-Catherine de Marneffe; Ivan Vladimir Meza Ruiz . Association for Computational Linguistics, 2022. p. 269-281 (Findings of the Association for Computational Linguistics: NAACL - Findings).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with host publication)peer-review

Download Statistics

No data available