Towards leveraging latent knowledge and Dialogue context for real-world conversational question answering

TL;DR

This paper introduces a neural Retrieval-Reading system that leverages latent knowledge and dialogue context, enhanced with a TFIDF-based summarizer, to improve real-world conversational question answering without external knowledge sources.

Contribution

It proposes a novel Retrieval-Reading framework with a context summarizer to effectively utilize internal dialogue data for better question answering.

Findings

The system significantly improves answer quality over baseline models.

The context summarizer enhances retrieval and reading performance.

Leveraging latent knowledge reduces dependence on external sources.

Abstract

In many real-world scenarios, the absence of external knowledge source like Wikipedia restricts question answering systems to rely on latent internal knowledge in limited dialogue data. In addition, humans often seek answers by asking several questions for more comprehensive information. As the dialog becomes more extensive, machines are challenged to refer to previous conversation rounds to answer questions. In this work, we propose to leverage latent knowledge in existing conversation logs via a neural Retrieval-Reading system, enhanced with a TFIDF-based text summarizer refining lengthy conversational history to alleviate the long context issue. Our experiments show that our Retrieval-Reading system can exploit retrieved background knowledge to generate significantly better answers. The results also indicate that our context summarizer significantly helps both the retriever and the reader by introducing more concise and less noisy contextual information.