Modeling Task Interactions in Document-Level Joint Entity and Relation Extraction
We target on the document-level relation extraction in an end-to-end setting, where the model needs to jointly perform mention extraction, coreference resolution (COREF) and relation extraction (RE) at once, and gets evaluated in an entity-centric way. Especially, we address the two-way interaction between COREF and RE that has not been the focus by previous work, and propose to introduce explicit interaction namely Graph Compatibility (GC) that is specifically designed to leverage task characteristics, bridging decisions of two tasks for direct task interference. Our experiments are conducted on DocRED and DWIE; in addition to GC, we implement and compare different multi-task settings commonly adopted in previous work, including pipeline, shared encoders, graph propagation, to examine the effectiveness of different interactions. The result shows that GC achieves the best performance by up to 2.3/5.1 F1 improvement over the baseline.
Code (0)
등록된 구현이 없습니다.
Tasks
coreference-resolutionCoreference ResolutionDocument-level Relation ExtractionJoint Entity and Relation ExtractionRelationRelation ExtractionSimilar Papers 제목 키워드 기반
Do the Benefits of Joint Models for Relation Extraction Extend to Document-level Tasks?
Two distinct approaches have been proposed for relational triple extraction - pipeline and joint. Joint models, which capture interactions across triples, are the more recent development, and have been shown to outperfor…
RelationRelation ExtractionSentenceFUM: Fine-grained and Fast User Modeling for News Recommendation
User modeling is important for news recommendation. Existing methods usually first encode user's clicked news into news embeddings independently and then aggregate them into user embedding. However, the word-level intera…
News RecommendationHave my arguments been replied to? Argument Pair Extraction as Machine Reading Comprehension
Argument pair extraction (APE) aims to automatically mine argument pairs from two interrelated argumentative documents. Existing studies typically identify argument pairs indirectly by predicting sentence-level relations…
Argument MiningArgument Pair Extraction (APE)Machine Reading ComprehensionReading Comprehension+1ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation
We propose ChainHOI, a novel approach for text-driven human-object interaction (HOI) generation that explicitly models interactions at both the joint and kinetic chain levels. Unlike existing methods that implicit…
Human-Object Interaction DetectionHuman-Object Interaction GenerationExploring Sentence Community for Document-Level Event Extraction
Document-level event extraction is critical to various natural language processing tasks for providing structured information. Existing approaches by sequential modeling neglect the complex logic structures for long text…
Community DetectionDocument-level Event ExtractionEvent ExtractionGraph Attention+1