Supervised Relation Classification as Two-way Span-Prediction
Most of the current supervised relation classification (RC) algorithms use a single embedding to represent the relation between a pair of entities. We argue that a better approach is to treat the RC task as a Span-Prediction (SP) problem, similar to Question Answering (QA). We present an SP-based system for RC and evaluate its performance compared to the embedding-based system. We demonstrate that by adding a few improvements, the supervised SP objective works significantly better than the standard classification-based objective. We achieve state-of-the-art results on the TACRED, SemEval task 8, and the CRE datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationPredictionQuestion AnsweringRelationRelation ClassificationVocal Bursts Valence PredictionSimilar Papers 제목 키워드 기반
Relation Classification as Two-way Span-Prediction
The current supervised relation classification (RC) task uses a single embedding to represent the relation between a pair of entities. We argue that a better approach is to treat the RC task as span-prediction (SP) probl…
ClassificationGeneral ClassificationPredictionQuestion Answering+4Global Constraints with Prompting for Zero-Shot Event Argument Classification
Determining the role of event arguments is a crucial subtask of event extraction. Most previous supervised models leverage costly annotations, which is not practical for open-domain applications. In this work, we propose…
Event ExtractionLanguage ModelingLanguage ModellingDiscourse Relation Prediction: Revisiting Word Pairs with Convolutional Networks
Word pairs across argument spans have been shown to be effective for predicting the discourse relation between them. We propose an approach to distill knowledge from word pairs for discourse relation classification with …
Binary ClassificationClassificationGeneral ClassificationPrediction+3Relation Classification with Entity Type Restriction
Relation classification aims to predict a relation between two entities in a sentence. The existing methods regard all relations as the candidate relations for the two entities in a sentence. These methods neglect the re…
ClassificationRelationRelation ClassificationRelation Extraction+2ClaHF: A Human Feedback-inspired Reinforcement Learning Framework for Improving Classification Tasks
Text classification models are typically trained via supervised fine-tuning (SFT). However, SFT essentially performs behavior cloning from instance-wise labels and thus fails to adequately capture relative preference rel…
Reinforcement LearningText Classification