paper-with-me

홈 › Papers

Zero-shot Cross-lingual Conversational Semantic Role Labeling

2021-11-16 · ACL ARR November 2021 11 · Anonymous

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 cross-lingual model not only outperforms baselines by large margins but it is also robust to low-resource scenarios. More importantly, we confirm the usefulness of CSRL to English conversational tasks such as question-in-context rewriting and multi-turn dialogue response generation by incorporating the CSRL information into the downstream conversation-based models. We believe this finding is significant and will facilitate the research of English dialogue tasks which suffer the problems of ellipsis and anaphora.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Response GenerationSemantic Role LabelingTranslation

Similar Papers 제목 키워드 기반

Zero-shot Cross-lingual Conversational Semantic Role Labeling

2022-04-11 · Findings (NAACL) 2022 7 · Han Wu, Haochen Tan, Kun Xu, Shuqi Liu 외

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 pa…

Response GenerationSemantic Role Labeling

Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Research on (multi-domain) task-oriented dialog (TOD) has predominantly focused on the English language, primarily due to the shortage of robust TOD datasets in other languages, preventing the systematic investigation of…

Cross-Lingual Transferdialog state trackingRetrieval

Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog

2022-05-20 · NAACL 2022 7 · Chia-Chien Hung, Anne Lauscher, Ivan Vulić, Simone Paolo Ponzetto 외

Research on (multi-domain) task-oriented dialog (TOD) has predominantly focused on the English language, primarily due to the shortage of robust TOD datasets in other languages, preventing the systematic investigation of…

Cross-Lingual Transferdialog state trackingRetrieval

Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning

2023-04-03 · Lifu Tu, Jin Qu, Semih Yavuz, Shafiq Joty 외

Cross-lingual transfer of language models trained on high-resource languages like English has been widely studied for many NLP tasks, but focus on conversational tasks has been rather limited. This is partly due to the h…

Cross-Lingual Transferintent-classificationIntent Classificationslot-filling+2

ChatZero:Zero-shot Cross-Lingual Dialogue Generation via Pseudo-Target Language

2024-08-16 · Yongkang Liu, Feng Shi, Daling Wang, Yifei Zhang 외

Although large language models(LLMs) show amazing capabilities, among various exciting applications discovered for LLMs fall short in other low-resource languages. Besides, most existing methods depend on large-scale dia…

Contrastive LearningDialogue Generation