Selecting Query-bag as Pseudo Relevance Feedback for Information-seeking Conversations

TL;DR

This paper introduces a novel Query-bag based Pseudo Relevance Feedback framework (QB-PRF) that improves response selection in information-seeking dialogue systems by leveraging related queries to enhance semantic understanding.

Contribution

The paper proposes a new QB-PRF framework with modules for selecting and fusing related queries, trained via contrastive learning and attention mechanisms, to improve response ranking.

Findings

QB-PRF outperforms strong baselines on benchmark datasets.

The framework enhances semantic representation of queries.

Experimental results validate the effectiveness of the proposed modules.

Abstract

Information-seeking dialogue systems are widely used in e-commerce systems, with answers that must be tailored to fit the specific settings of the online system. Given the user query, the information-seeking dialogue systems first retrieve a subset of response candidates, then further select the best response from the candidate set through re-ranking. Current methods mainly retrieve response candidates based solely on the current query, however, incorporating similar questions could introduce more diverse content, potentially refining the representation and improving the matching process. Hence, in this paper, we proposed a Query-bag based Pseudo Relevance Feedback framework (QB-PRF), which constructs a query-bag with related queries to serve as pseudo signals to guide information-seeking conversations. Concretely, we first propose a Query-bag Selection module (QBS), which utilizes contrastive learning to train the selection of synonymous queries in an unsupervised manner by leveraging the representations learned from pre-trained VAE. Secondly, we come up with a Query-bag Fusion module (QBF) that fuses synonymous queries to enhance the semantic representation of the original query through multidimensional attention computation. We verify the effectiveness of the QB-PRF framework on two competitive pretrained backbone models, including BERT and GPT-2. Experimental results on two benchmark datasets show that our framework achieves superior performance over strong baselines.