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 (4)

• Understanding the Behaviors of BERT in Ranking
• Simple Applications of BERT for Ad Hoc Document Retrieval
• Open Sesame: Getting Inside BERT's Linguistic Knowledge
• Lexical Query Modeling in Session Search

Cited by in corpus (14)

• Few-Shot Conversational Dense Retrieval
• Zero-shot Query Contextualization for Conversational Search
• Simulating and Modeling the Risk of Conversational Search
• News Article Retrieval in Context for Event-centric Narrative Creation
• A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answering
• A Dataset for Sentence Retrieval for Open-Ended Dialogues
• Controlling the Risk of Conversational Search via Reinforcement Learning
• Wizard of Search Engine: Access to Information Through Conversations with Search Engines
• Knowledge-driven Answer Generation for Conversational Search
• Leveraging Query Resolution and Reading Comprehension for Conversational Passage Retrieval
• Learning to Ask Conversational Questions by Optimizing Levenshtein Distance
• Combining Lexical and Dense Retrieval for Computationally Efficient Multi-hop Question Answering
• MICROS: Mixed-Initiative ConveRsatiOnal Systems Workshop
• BERT Embeddings Can Track Context in Conversational Search