Few-shot Conversational Dense Retrieval
2021 · Shi Yu, Zhenghao Liu, Chenyan Xiong, et al.
Abstract
Dense retrieval (DR) has the potential to resolve the query understanding challenge in conversational search by matching in the learned embedding space. However, this adaptation is challenging due to DR models' extra needs for supervision signals and the long-tail nature of conversational search. In this paper, we present a Conversational Dense Retrieval system, ConvDR, that learns contextualized embeddings for multi-turn conversational queries and retrieves documents solely using embedding dot products. In addition, we grant ConvDR few-shot ability using a teacher-student framework, where we employ an ad hoc dense retriever as the teacher, inherit its document encodings, and learn a student query encoder to mimic the teacher embeddings on oracle reformulated queries. Our experiments on TREC CAsT and OR-QuAC demonstrate ConvDR's effectiveness in both few-shot and fully-supervised settings. It outperforms previous systems that operate in the sparse word space, matches the retrieval accu
Authors
(none)
Tags
Stats
Related papers
- CONVERSER: Few-shot Conversational Dense Retrieval With Synthetic Data Generation (2023)8.25
- Interpreting Dense Retrieval As Mixture Of Topics (2021)0.00
- Dense Passage Retrieval In Conversational Search (2025)0.00
- Contextualized Query Embeddings For Conversational Search (2021)10.21
- Disentangled Modeling Of Domain And Relevance For Adaptable Dense Retrieval (2022)0.00
- How To Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval (2023)11.39
- Efficiently Teaching An Effective Dense Retriever With Balanced Topic Aware Sampling (2021)17.07
- Interpreting Conversational Dense Retrieval By Rewriting-enhanced Inversion Of Session Embedding (2024)6.77