Iterative Relevance Feedback for Answer Passage Retrieval with Passage-level Semantic Match
Relevance feedback techniques assume that users provide relevance judgments for the top k (usually 10) documents and then re-rank using a new query model based on those judgments. Even though this is effective, there has been little research recently on this topic because requiring users to provide substantial feedback on a result list is impractical in a typical web search scenario. In new environments such as voice-based search with smart home devices, however, feedback about result quality can potentially be obtained during users' interactions with the system. Since there are severe limitations on the length and number of results that can be presented in a single interaction in this environment, the focus should move from browsing result lists to iterative retrieval and from retrieving documents to retrieving answers. In this paper, we study iterative relevance feedback techniques with a focus on retrieving answer passages. We first show that iterative feedback is more effective than the top-k approach for answer retrieval. Then we propose an iterative feedback model based on passage-level semantic match and show that it can produce significant improvements compared to both word-based iterative feedback models and those based on term-level semantic similarity.
Code (0)
등록된 구현이 없습니다.
Tasks
Passage RetrievalRetrievalSemantic SimilaritySemantic Textual SimilaritySimilar Papers 제목 키워드 기반
Revisiting Iterative Relevance Feedback for Document and Passage Retrieval
As more and more search traffic comes from mobile phones, intelligent assistants, and smart-home devices, new challenges (e.g., limited presentation space) and opportunities come up in information retrieval. Previously, …
Information RetrievalPassage RetrievalRetrievalOptimizing Test-Time Query Representations for Dense Retrieval
Recent developments of dense retrieval rely on quality representations of queries and contexts from pre-trained query and context encoders. In this paper, we introduce TOUR (Test-Time Optimization of Query Representation…
Contrastive LearningInformation RetrievalOpen-Domain Question AnsweringPassage Retrieval+3Iterative Utility Judgment Framework via LLMs Inspired by Relevance in Philosophy
Utility and topical relevance are critical measures in information retrieval (IR), reflecting system and user perspectives, respectively. While topical relevance has long been emphasized, utility is a higher standard of …
Answer GenerationInformation RetrievalPassage RetrievalPhilosophy+4Relevance-guided Supervision for OpenQA with ColBERT
Systems for Open-Domain Question Answering (OpenQA) generally depend on a retriever for finding candidate passages in a large corpus and a reader for extracting answers from those passages. In much recent work, the retri…
Natural QuestionsOpen-Domain Question AnsweringQuestion AnsweringRetrieval+1ADORE: Iterative Query Expansion with Retrieval-Grounded Relevance Feedback
LLM-based query expansion improves retrieval by enriching the original query with additional context. Yet most methods remain generation-driven, producing plausible pseudo-documents or expansions without checking how the…