Query Resolution for Conversational Search with Limited Supervision

Abstract

In this work we focus on multi-turn passage retrieval as a crucial component of conversational search. One of the key challenges in multi-turn passage retrieval comes from the fact that the current turn query is often underspecified due to zero anaphora, topic change, or topic return. Context from the conversational history can be used to arrive at a better expression of the current turn query, defined as the task of query resolution. In this paper, we model the query resolution task as a binary term classification problem: for each term appearing in the previous turns of the conversation decide whether to add it to the current turn query or not. We propose QuReTeC (Query Resolution by Term Classification), a neural query resolution model based on bidirectional transformers. We propose a distant supervision method to automatically generate training data by using query-passage relevance labels. Such labels are often readily available in a collection either as human annotations or inferred from user interactions. We show that QuReTeC outperforms state-of-the-art models, and furthermore, that our distant supervision method can be used to substantially reduce the amount of human-curated data required to train QuReTeC. We incorporate QuReTeC in a multi-turn, multi-stage passage retrieval architecture and demonstrate its effectiveness on the TREC CAsT dataset.

SIGIR 2020 full conference paper

References in corpus (11)

• Data Augmentation for Low-Resource Neural Machine Translation
• CEDR: Contextualized Embeddings for Document Ranking
• Understanding the Behaviors of BERT in Ranking
• Neural Approaches to Conversational AI
• Simple Applications of BERT for Ad Hoc Document Retrieval
• QuAC : Question Answering in Context
• Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning
• A Term-Based Methodology for Query Reformulation Understanding
• Weakly-supervised Contextualization of Knowledge Graph Facts
• Open Sesame: Getting Inside BERT's Linguistic Knowledge
• Lexical Query Modeling in Session Search

Cited by in corpus (25)

• Advances and Challenges in Conversational Recommender Systems: A Survey
• Few-Shot Conversational Dense Retrieval
• Query Performance Prediction: From Ad-hoc to Conversational Search
• Exploiting Simulated User Feedback for Conversational Search: Ranking, Rewriting, and Beyond
• Zero-shot Query Contextualization for Conversational Search
• Simulating and Modeling the Risk of Conversational Search
• Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting
• Data Fusion of Synthetic Query Variants With Generative Large Language Models
• News Article Retrieval in Context for Event-centric Narrative Creation
• Conversations with Search Engines: SERP-based Conversational Response Generation
• A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answering
• A Dataset for Sentence Retrieval for Open-Ended Dialogues
• Rewriting Conversational Utterances with Instructed Large Language Models
• Improving Conversational Passage Re-ranking with View Ensemble
• Contextualized Query Embeddings for Conversational Search
• Controlling the Risk of Conversational Search via Reinforcement Learning
• Wizard of Search Engine: Access to Information Through Conversations with Search Engines
• Efficient Conversational Search via Topical Locality in Dense Retrieval
• Knowledge-driven Answer Generation for Conversational Search
• MICROS: Mixed-Initiative ConveRsatiOnal Systems Workshop
• MS MARCO: Benchmarking Ranking Models in the Large-Data Regime
• Learning to Ask Conversational Questions by Optimizing Levenshtein Distance
• BERT Embeddings Can Track Context in Conversational Search
• Leveraging Query Resolution and Reading Comprehension for Conversational Passage Retrieval
• Combining Lexical and Dense Retrieval for Computationally Efficient Multi-hop Question Answering