Grounded Dialogue Generation with Cross-encoding Re-ranker, Grounding Span Prediction, and Passage Dropout
Refereed conference paper presented and published in conference proceedings


Full Text

Times Cited

Other information
AbstractMultiDoc2Dial presents an important challenge on modeling dialogues grounded with multiple documents. This paper proposes a pipeline system of "retrieve, re-rank, and generate", where each component is individually optimized. This enables the passage re-ranker and response generator to fully exploit training with ground-truth data. Furthermore, we use a deep crossencoder trained with localized hard negative passages from the retriever. For the response generator, we use grounding span prediction as an auxiliary task to be jointly trained with the main task of response generation. We also adopt a passage dropout and regularization technique to improve response generation performance. Experimental results indicate that the system clearly surpasses the competitive baseline and our team CPII-NLP ranked 1st among the public submissions on ALL four leaderboards based on the sum of F1, SacreBLEU, METEOR and RougeL scores.
All Author(s) ListKun Li, Tianhua Zhang, Liping Tang, Junan Li, Hongyuan Lu, Xixin Wu, Helen Meng
Name of ConferenceDialDoc Workshop
Start Date of Conference26/05/2022
End Date of Conference26/05/2022
Place of ConferenceDublin
Country/Region of ConferenceIreland
Proceedings TitleDialDoc 2022 - Proceedings of the 2nd DialDoc Workshop on Document-Grounded Dialogue and Conversational Question Answering
Year2022
Pages123 - 129
LanguagesEnglish-United Kingdom

Last updated on 2024-09-04 at 00:33