Zero-shot Cross-lingual Conversational Semantic Role Labeling
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Response GenerationSemantic Role LabelingTranslationSimilar Papers 제목 키워드 기반
Zero-shot Cross-lingual Conversational Semantic Role Labeling
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 LabelingMulti2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog
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 trackingRetrievalMulti2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog
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 trackingRetrievalEfficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning
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+2ChatZero:Zero-shot Cross-Lingual Dialogue Generation via Pseudo-Target Language
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