Iterative Document-level Information Extraction via Imitation Learning
We present a novel iterative extraction model, IterX, for extracting complex relations, or templates (i.e., N-tuples representing a mapping from named slots to spans of text) within a document. Documents may feature zero or more instances of a template of any given type, and the task of template extraction entails identifying the templates in a document and extracting each template's slot values. Our imitation learning approach casts the problem as a Markov decision process (MDP), and relieves the need to use predefined template orders to train an extractor. It leads to state-of-the-art results on two established benchmarks -- 4-ary relation extraction on SciREX and template extraction on MUC-4 -- as well as a strong baseline on the new BETTER Granular task.
Code (2)
Tasks
4-ary Relation ExtractionImitation LearningRelation ExtractionSimilar Papers 제목 키워드 기반
Harvesting Events from Multiple Sources: Towards a Cross-Document Event Extraction Paradigm
Document-level event extraction aims to extract structured event information from unstructured text. However, a single document often contains limited event information and the roles of different event arguments may be b…
coreference-resolutionCoreference ResolutionDocument-level Event ExtractionEvent ExtractionA Survey of Document-Level Information Extraction
Document-level information extraction (IE) is a crucial task in natural language processing (NLP). This paper conducts a systematic review of recent document-level IE literature. In addition, we conduct a thorough error …
coreference-resolutionCoreference ResolutionSurveyTowards Better Document-level Relation Extraction via Iterative Inference
Document-level relation extraction (RE) aims to extract the relations between entities from the input document that usually containing many difficultly-predicted entity pairs whose relations can only be predicted through…
Contrastive LearningDocument-level Relation ExtractionRelationRelation ExtractionSynDoc: A Hybrid Discriminative-Generative Framework for Enhancing Synthetic Domain-Adaptive Document Key Information Extraction
Domain-specific Visually Rich Document Understanding (VRDU) presents significant challenges due to the complexity and sensitivity of documents in fields such as medicine, finance, and material science. Existing Large (Mu…
Key Information ExtractionSynthetic Data GenerationDomain AdaptationAdaQE-CG: Adaptive Query Expansion for Web-Scale Generative AI Model and Data Card Generation
Transparent and standardized documentation is essential for building trustworthy generative AI (GAI) systems. However, existing automated methods for generating model and data cards still face three major challenges: (i)…
Information Extraction