Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting

2020/05/05 by Sheng-Chieh Lin, Jheng-Hong Yang, Lin, Sheng-Chieh +10
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling #cs.AI #cs.CL #cs.IR

paper · pdf · doi:10.48550/arxiv.2005.02230

28 pages. Accepted to ACM Transactions on Information Systems, Special Issue on Conversational Search and Recommendation. The first two authors contributed equally. Code: https://github.com/castorini/chatty-goose

openalex publication_date 2020/05/05 · arxiv created 2021/03/11 · arxiv updated 2021/03/12 · openalex created_date 2021/03/15 · openalex updated_date 2026/07/28

Abstract

Conversational search plays a vital role in conversational information seeking. As queries in information seeking dialogues are ambiguous for traditional ad-hoc information retrieval (IR) systems due to the coreference and omission resolution problems inherent in natural language dialogue, resolving these ambiguities is crucial. In this paper, we tackle conversational passage retrieval (ConvPR), an important component of conversational search, by addressing query ambiguities with query reformulation integrated into a multi-stage ad-hoc IR system. Specifically, we propose two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting. For the former, we expand conversational queries using important terms extracted from the conversational context with frequency-based signals. For the latter, we reformulate conversational queries into natural, standalone, human-understandable queries with a pretrained sequence-tosequence model. Detailed analyses of the two CQR methods are provided quantitatively and qualitatively, explaining their advantages, disadvantages, and distinct behaviors. Moreover, to leverage the strengths of both CQR methods, we propose combining their output with reciprocal rank fusion, yielding state-of-the-art retrieval effectiveness, 30% improvement in terms of NDCG@3 compared to the best submission of TREC CAsT 2019.

Citations

• Sequence to Sequence Learning with Neural Networks
• Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
• A Survey on Transfer Learning
• Quasar: Datasets for Question Answering by Search and Reading
• Know What You Don't Know: Unanswerable Questions for SQuAD
• Passage Re-ranking with BERT
• Using Pre-Training Can Improve Model Robustness and Uncertainty
• XLNet: Generalized Autoregressive Pretraining for Language Understanding
• FlowQA: Grasping Flow in History for Conversational Machine Comprehension
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• On Extractive and Abstractive Neural Document Summarization with Transformer Language Models
• Multi-Stage Document Ranking with BERT
• Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models

Related

• A Surprisingly Simple yet Effective Multi-Query Rewriting Method for Conversational Passage Retrieval
• Leveraging Query Resolution and Reading Comprehension for Conversational Passage Retrieval
• IterCQR: Iterative Conversational Query Reformulation with Retrieval Guidance
• Dense Passage Retrieval in Conversational Search
• Generating Multi-Aspect Queries for Conversational Search