Cross-Domain Modeling of Sentence-Level Evidence for Document Retrieval
This paper applies BERT to ad hoc document retrieval on news articles, which requires addressing two challenges: relevance judgments in existing test collections are typically provided only at the document level, and documents often exceed the length that BERT was designed to handle. Our solution is to aggregate sentence-level evidence to rank documents. Furthermore, we are able to leverage passage-level relevance judgments fortuitously available in other domains to fine-tune BERT models that are able to capture cross-domain notions of relevance, and can be directly used for ranking news articles. Our simple neural ranking models achieve state-of-the-art effectiveness on three standard test collections.
Code (0)
등록된 구현이 없습니다.
Tasks
ArticlesRetrievalSentenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering
Traditional Retrieval-Augmented Generation (RAG) effectively supports single-hop question answering with large language models but faces significant limitations in multi-hop question answering tasks, which require combin…
Multi-hop Question AnsweringAnswer GenerationMultimodal Relation Extraction with Cross-Modal Retrieval and Synthesis
Multimodal relation extraction (MRE) is the task of identifying the semantic relationships between two entities based on the context of the sentence image pair. Existing retrieval-augmented approaches mainly focused on m…
Cross-Modal RetrievalObjectRelationRelation Extraction+2Hierarchical Evidence Set Modeling for Automated Fact Extraction and Verification
Automated fact extraction and verification is a challenging task that involves finding relevant evidence sentences from a reliable corpus to verify the truthfulness of a claim. Existing models either (i) concatenate all …
Claim VerificationSentenceRT-SDGOD: Real-Time Single-Domain Generalized Object Detection
In real-world deployment under strict real-time constraints, weather and imaging variations induce significant distribution shifts, severely degrading detectors. Single-Domain Generalized Object Detection aims to mitigat…
Representation LearningDomain GeneralizationObject DetectionR$^2$F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language Inference
Document-level natural language inference (DOCNLI) is a new challenging task in natural language processing, aiming at judging the entailment relationship between a pair of hypothesis and premise documents. Current datas…
Natural Language InferenceRetrievalSentence