paper-with-me

Papers

Learning Diverse Document Representations with Deep Query Interactions for Dense Retrieval

2022-08-08 · Zehan Li, Nan Yang, Liang Wang, Furu Wei

In this paper, we propose a new dense retrieval model which learns diverse document representations with deep query interactions. Our model encodes each document with a set of generated pseudo-queries to get query-informed, multi-view document representations. It not only enjoys high inference efficiency like the vanilla dual-encoder models, but also enables deep query-document interactions in document encoding and provides multi-faceted representations to better match different queries. Experiments on several benchmarks demonstrate the effectiveness of the proposed method, out-performing strong dual encoder baselines.The code is available at \url{https://github.com/jordane95/dual-cross-encoder

📄 PDF Abstract BibTeX arXiv:2208.04232

Code (1)

jordane95/dual-cross-encoder 공식 구현 jax

Tasks

Retrieval

Similar Papers 제목 키워드 기반

CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion

2022-12-18 · Xingwei He, Yeyun Gong, A-Long Jin, Hang Zhang 외

The dual-encoder has become the de facto architecture for dense retrieval. Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between…

Passage RetrievalRetrieval

Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback

2021-08-30 · HongChien Yu, Chenyan Xiong, Jamie Callan

Dense retrieval systems conduct first-stage retrieval using embedded representations and simple similarity metrics to match a query to documents. Its effectiveness depends on encoded embeddings to capture the semantics o…

Retrieval

More Robust Dense Retrieval with Contrastive Dual Learning

2021-07-16 · Yizhi Li, Zhenghao Liu, Chenyan Xiong, Zhiyuan Liu

Dense retrieval conducts text retrieval in the embedding space and has shown many advantages compared to sparse retrieval. Existing dense retrievers optimize representations of queries and documents with contrastive trai…

Contrastive LearningInformation RetrievalRetrievalText Retrieval

Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Dense retrieval models, which aim at retrieving the most relevant document for an input query on a dense representation space, have gained considerable attention for their remarkable success. Yet, dense models require a …

Retrieval

Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation

2022-03-15 · ACL 2022 5 · Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang 외

Dense retrieval models, which aim at retrieving the most relevant document for an input query on a dense representation space, have gained considerable attention for their remarkable success. Yet, dense models require a …

Data AugmentationInformation RetrievalPassage RetrievalRetrieval