Self-supervised Dialogue Learning for Spoken Conversational Question Answering
This addresses the challenge of building robust SCQA systems for applications like voice assistants by improving dialogue coherence, though it is incremental as it builds on pre-trained language models.
The paper tackles the problem of low-quality and incoherent corpora in spoken conversational question answering (SCQA) by introducing a self-supervised learning approach with tasks like incoherence discrimination and insertion detection, achieving state-of-the-art results on the Spoken-CoQA dataset.
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.