Back to Search
Start Over
Self-Supervised Dialogue Learning for Spoken Conversational Question Answering
- Source :
- Interspeech 2021.
- Publication Year :
- 2021
- Publisher :
- ISCA, 2021.
-
Abstract
- In spoken conversational question answering (SCQA), the answer to the corresponding question is generated by retrieving and then analyzing a fixed spoken document, including multi-part conversations. Most SCQA systems have considered only retrieving information from ordered utterances. However, the sequential order of dialogue is important to build a robust spoken conversational question answering system, and the changes of utterances order may severely result in low-quality and incoherent corpora. To this end, we introduce a self-supervised learning approach, including incoherence discrimination, insertion detection, and question prediction, to explicitly capture the coreference resolution and dialogue coherence among spoken documents. Specifically, we design a joint learning framework where the auxiliary self-supervised tasks can enable the pre-trained SCQA systems towards more coherent and meaningful spoken dialogue learning. We also utilize the proposed self-supervised learning tasks to capture intra-sentence coherence. Experimental results demonstrate that our proposed method provides more coherent, meaningful, and appropriate responses, yielding superior performance gains compared to the original pre-trained language models. Our method achieves state-of-the-art results on the Spoken-CoQA dataset.<br />Comment: To Appear Interspeech 2021
- Subjects :
- FOS: Computer and information sciences
Computer Science - Machine Learning
Coreference
Computer Science - Computation and Language
Computer Science - Artificial Intelligence
Computer science
business.industry
Resolution (logic)
computer.software_genre
Machine Learning (cs.LG)
Artificial Intelligence (cs.AI)
Audio and Speech Processing (eess.AS)
Order (business)
FOS: Electrical engineering, electronic engineering, information engineering
Question answering
Artificial intelligence
Language model
business
Computation and Language (cs.CL)
computer
Natural language processing
Coherence (linguistics)
Electrical Engineering and Systems Science - Audio and Speech Processing
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- Interspeech 2021
- Accession number :
- edsair.doi.dedup.....0e7b6b9829ed6667f0e26822480c43b5