Improving Document Retrieval Coherence for Semantically Equivalent Queries
Dense Retrieval (DR) models have proven to be effective for Document Retrieval and Information Grounding tasks. Usually, these models are trained and optimized for improving the relevance of top-ranked documents for a given query. Previous work has shown that popular DR models are sensitive to the query and document lexicon: small variations of it may lead to a significant difference in the set of retrieved documents. In this paper, we propose a variation of the Multi-Negative Ranking loss for training DR that improves the coherence of models in retrieving the same documents with respect to semantically similar queries. The loss penalizes discrepancies between the top-k ranked documents retrieved for diverse but semantic equivalent queries. We conducted extensive experiments on various datasets, MS-MARCO, Natural Questions, BEIR, and TREC DL 19/20. The results show that (i) models optimizes by our loss are subject to lower sensitivity, and, (ii) interestingly, higher accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
Natural QuestionsSimilar Papers 제목 키워드 기반
LAMAR: An Open Language-Aware Multilingual Alignment Reranker
In multilingual retrieval augmented generation, a retriever can retrieve relevant documents written in multiple languages, which are subsequently reranked before answer generation. However, it remains unclear whether exi…
Answer GenerationMLDocRAG: Multimodal Long-Context Document Retrieval Augmented Generation
Understanding multimodal long-context documents that comprise multimodal chunks such as paragraphs, figures, and tables is challenging due to (1) cross-modal heterogeneity to localize relevant information across modaliti…
Long-Context UnderstandingQuestion AnsweringTowards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark
Document image retrieval (DIR) aims to retrieve document images from a gallery according to a given query. Existing DIR methods are primarily based on image queries that retrieve documents within the same coarse semantic…
Image RetrievalTowards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark
Document image retrieval (DIR) aims to retrieve document images from a gallery according to a given query. Existing DIR methods are primarily based on image queries that retrieve documents within the same coarse sema…
document understandingImage RetrievalOptical Character Recognition (OCR)RetrievalKnowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrieval
Large language models (LLMs) have been used to generate query expansions augmenting original queries for improving information search. Recent studies also explore providing LLMs with initial retrieval results to generate…
Retrieval