Latent Retrieval for Weakly Supervised Open Domain Question Answering
Recent work on open domain question answering (QA) assumes strong supervision of the supporting evidence and/or assumes a blackbox information retrieval (IR) system to retrieve evidence candidates. We argue that both are suboptimal, since gold evidence is not always available, and QA is fundamentally different from IR. We show for the first time that it is possible to jointly learn the retriever and reader from question-answer string pairs and without any IR system. In this setting, evidence retrieval from all of Wikipedia is treated as a latent variable. Since this is impractical to learn from scratch, we pre-train the retriever with an Inverse Cloze Task. We evaluate on open versions of five QA datasets. On datasets where the questioner already knows the answer, a traditional IR system such as BM25 is sufficient. On datasets where a user is genuinely seeking an answer, we show that learned retrieval is crucial, outperforming BM25 by up to 19 points in exact match.
Code (3)
Tasks
Information RetrievalOpen-Domain Question AnsweringQuestion AnsweringRetrievalSimilar Papers 제목 키워드 기반
CLAIR: CLIP-Aided Weakly Supervised Zero-Shot Cross-Domain Image Retrieval
The recent growth of large foundation models that can easily generate pseudo-labels for huge quantity of unlabeled data makes unsupervised Zero-Shot Cross-Domain Image Retrieval (UZS-CDIR) less relevant. In this paper, w…
Zero-shot GeneralizationImage RetrievalLoGAN: Latent Graph Co-Attention Network for Weakly-Supervised Video Moment Retrieval
The goal of weakly-supervised video moment retrieval is to localize the video segment most relevant to the given natural language query without access to temporal annotations during training. Prior strongly- and weakly-s…
Moment RetrievalRetrievalHybrid-Learning Video Moment Retrieval across Multi-Domain Labels
Video moment retrieval (VMR) is to search for a visual temporal moment in an untrimmed raw video by a given text query description (sentence). Existing studies either start from collecting exhaustive frame-wise annotatio…
Moment RetrievalRetrievalSentenceText Matching+1W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering
In knowledge-intensive tasks such as open-domain question answering (OpenQA), large language models (LLMs) often struggle to generate factual answers, relying solely on their internal (parametric) knowledge. To address t…
Open-Domain Question AnsweringQuestion AnsweringRAGRetrieval+1wMAN: WEAKLY-SUPERVISED MOMENT ALIGNMENT NETWORK FOR TEXT-BASED VIDEO SEGMENT RETRIEVAL
Given a video and a sentence, the goal of weakly-supervised video moment retrieval is to locate the video segment which is described by the sentence without having access to temporal annotations during training. Instead…
Moment RetrievalRetrievalSentence