Knowledge-driven Answer Generation for Conversational Search

TL;DR

This paper introduces a knowledge-driven approach for conversational search answer generation that leverages a conversation-specific entities' knowledge graph to produce more relevant and concise answers, outperforming baseline methods.

Contribution

It proposes a novel method that uses a conversation-specific knowledge graph to bias answer generation in open-domain conversational search, improving relevance and conciseness.

Findings

Outperforms baseline methods in search-answer generation tasks.

Effectively exploits entities knowledge throughout the conversation.

Enhances answer relevance and conciseness using a knowledge graph bias.

Abstract

The conversational search paradigm introduces a step change over the traditional search paradigm by allowing users to interact with search agents in a multi-turn and natural fashion. The conversation flows naturally and is usually centered around a target field of knowledge. In this work, we propose a knowledge-driven answer generation approach for open-domain conversational search, where a conversation-wide entities' knowledge graph is used to bias search-answer generation. First, a conversation-specific knowledge graph is extracted from the top passages retrieved with a Transformer-based re-ranker. The entities knowledge-graph is then used to bias a search-answer generator Transformer towards information rich and concise answers. This conversation specific bias is computed by identifying the most relevant passages according to the most salient entities of that particular conversation. Experiments show that the proposed approach successfully exploits entities knowledge along the conversation, and outperforms a set of baselines on the search-answer generation task.