Document-Level Relation Extraction with Sentences Importance Estimation and Focusing
Document-level relation extraction (DocRE) aims to determine the relation between two entities from a document of multiple sentences. Recent studies typically represent the entire document by sequence- or graph-based models to predict the relations of all entity pairs. However, we find that such a model is not robust and exhibits bizarre behaviors: it predicts correctly when an entire test document is fed as input, but errs when non-evidence sentences are removed. To this end, we propose a Sentence Importance Estimation and Focusing (SIEF) framework for DocRE, where we design a sentence importance score and a sentence focusing loss, encouraging DocRE models to focus on evidence sentences. Experimental results on two domains show that our SIEF not only improves overall performance, but also makes DocRE models more robust. Moreover, SIEF is a general framework, shown to be effective when combined with a variety of base DocRE models.
Code (1)
Tasks
Dialog Relation ExtractionDocument-level Relation ExtractionRelationRelation ExtractionSentenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction
Document-level Relation Extraction (RE) is a more challenging task than sentence RE as it often requires reasoning over multiple sentences. Yet, human annotators usually use a small number of sentences to identify the re…
AllDocument-level Relation ExtractionGraph Neural NetworkRelation+2EIDER: Evidence-enhanced Document-level Relation Extraction
Document-level relation extraction (DocRE) aims at extracting the semantic relations among entity pairs in a document. In DocRE, a subset of the sentences in a document, called the evidence sentences, might be sufficient…
Document-level Relation ExtractionRelationRelation ExtractionSentenceFrom Bag of Sentences to Document: Distantly Supervised Relation Extraction via Machine Reading Comprehension
Distant supervision (DS) is a promising approach for relation extraction but often suffers from the noisy label problem. Traditional DS methods usually represent an entity pair as a bag of sentences and denoise labels us…
DenoisingMachine Reading ComprehensionReading ComprehensionRelation+3Mention-centered Graph Neural Network for Document-level Relation Extraction
Document-level relation extraction aims to discover relations between entities across a whole document. How to build the dependency of entities from different sentences in a document remains to be a great challenge. Curr…
Document-level Relation ExtractionGraph Neural NetworkRelationRelation Extraction+1Entity and Evidence Guided Document-Level Relation Extraction
Document-level relation extraction is a challenging task, requiring reasoning over multiple sentences to predict a set of relations in a document. In this paper, we propose a novel framework E2GRE (Entity and Evidence Gu…
Document-level Relation ExtractionLanguage ModelingLanguage ModellingRelation+1