paper-with-me

홈 › Papers

What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary

2022-12-20 · Ori Ram, Liat Bezalel, Adi Zicher, Yonatan Belinkov, Jonathan Berant, Amir Globerson

Dual encoders are now the dominant architecture for dense retrieval. Yet, we have little understanding of how they represent text, and why this leads to good performance. In this work, we shed light on this question via distributions over the vocabulary. We propose to interpret the vector representations produced by dual encoders by projecting them into the model's vocabulary space. We show that the resulting projections contain rich semantic information, and draw connection between them and sparse retrieval. We find that this view can offer an explanation for some of the failure cases of dense retrievers. For example, we observe that the inability of models to handle tail entities is correlated with a tendency of the token distributions to forget some of the tokens of those entities. We leverage this insight and propose a simple way to enrich query and passage representations with lexical information at inference time, and show that this significantly improves performance compared to the original model in zero-shot settings, and specifically on the BEIR benchmark.

📄 PDF Abstract BibTeX arXiv:2212.10380

Code (1)

oriram/dense-retrieval-projections 공식 구현

Tasks

Retrieval

Similar Papers 제목 키워드 기반

CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos

2022-04-01 · Shengyao Zhuang, Guido Zuccon

Current dense retrievers are not robust to out-of-domain and outlier queries, i.e. their effectiveness on these queries is much poorer than what one would expect. In this paper, we consider a specific instance of such qu…

Passage RetrievalRetrieval

Zero-Shot Dense Retrieval with Embeddings from Relevance Feedback

2024-10-28 · Nour Jedidi, Yung-Sung Chuang, Leslie Shing, James Glass

Building effective dense retrieval systems remains difficult when relevance supervision is not available. Recent work has looked to overcome this challenge by using a Large Language Model (LLM) to generate hypothetical d…

Language ModellingLarge Language ModelRetrieval

Interpreting Dense Retrieval as Mixture of Topics

2021-11-27 · Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo 외

Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success. Therefore, in this work, we conduct an interpretation study of rece…

Retrieval

A Contrastive Pre-training Approach to Learn Discriminative Autoencoder for Dense Retrieval

2022-08-21 · Xinyu Ma, Ruqing Zhang, Jiafeng Guo, Yixing Fan 외

Dense retrieval (DR) has shown promising results in information retrieval. In essence, DR requires high-quality text representations to support effective search in the representation space. Recent studies have shown that…

DecoderInformation RetrievalRetrieval

Deep Learning Based Dense Retrieval: A Comparative Study

2024-10-27 · Ming Zhong, Zhizhi Wu, Nanako Honda

Dense retrievers have achieved state-of-the-art performance in various information retrieval tasks, but their robustness against tokenizer poisoning remains underexplored. In this work, we assess the vulnerability of den…

Deep LearningInformation RetrievalPassage RetrievalRetrieval