Improving Document Representations by Generating Pseudo Query Embeddings for Dense Retrieval
arXiv:2105.03599
Abstract
Recently, the retrieval models based on dense representations have been gradually applied in the first stage of the document retrieval tasks, showing better performance than traditional sparse vector space models. To obtain high efficiency, the basic structure of these models is Bi-encoder in most cases. However, this simple structure may cause serious information loss during the encoding of documents since the queries are agnostic. To address this problem, we design a method to mimic the queries on each of the documents by an iterative clustering process and represent the documents by multiple pseudo queries (i.e., the cluster centroids). To boost the retrieval process using approximate nearest neighbor search library, we also optimize the matching function with a two-step score calculation procedure. Experimental results on several popular ranking and QA datasets show that our model can achieve state-of-the-art results.
arXiv comment11 pages, 2 figures, Accepted by ACL 2021
References in corpus (7)
- Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
- Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval
- Pretrained Transformers for Text Ranking: BERT and Beyond
- A Dual Embedding Space Model for Document Ranking
- Sparse, Dense, and Attentional Representations for Text Retrieval
- RepBERT: Contextualized Text Embeddings for First-Stage Retrieval
- Overview of the TREC 2021 deep learning track