BERT Embeddings Can Track Context in Conversational Search

TL;DR

This paper demonstrates that BERT embeddings effectively track conversational context, enhancing search relevance by understanding dialogue history through neural query rewriting and Transformer-based re-ranking.

Contribution

The work introduces a novel conversational search system that leverages BERT embeddings for context tracking and neural query rewriting to improve information retrieval accuracy.

Findings

Using BERT embeddings improves context understanding in conversations.

Neural query rewriting enhances relevance in conversational search.

Transformer-based re-ranking benefits from conversational context.

Abstract

The use of conversational assistants to search for information is becoming increasingly more popular among the general public, pushing the research towards more advanced and sophisticated techniques. In the last few years, in particular, the interest in conversational search is increasing, not only because of the generalization of conversational assistants but also because conversational search is a step forward in allowing a more natural interaction with the system. In this work, the focus is on exploring the context present of the conversation via the historical utterances and respective embeddings with the aim of developing a conversational search system that helps people search for information in a natural way. In particular, this system must be able to understand the context where the question is posed, tracking the current state of the conversation and detecting mentions to previous questions and answers. We achieve this by using a context-tracking component based on neural query-rewriting models. Another crucial aspect of the system is to provide the most relevant answers given the question and the conversational history. To achieve this objective, we used a Transformer-based re-ranking method and expanded this architecture to use the conversational context. The results obtained with the system developed showed the advantages of using the context present in the natural language utterances and in the neural embeddings generated throughout the conversation.