A Unified Architecture for Semantic Role Labeling and Relation Classification
This paper describes a unified neural architecture for identifying and classifying multi-typed semantic relations between words in a sentence. We investigate two typical and well-studied tasks: semantic role labeling (SRL) which identifies the relations between predicates and arguments, and relation classification (RC) which focuses on the relation between two entities or nominals. While mostly studied separately in prior work, we show that the two tasks can be effectively connected and modeled using a general architecture. Experiments on CoNLL-2009 benchmark datasets show that our SRL models significantly outperform state-of-the-art approaches. Our RC models also yield competitive performance with the best published records. Furthermore, we show that the two tasks can be trained jointly with multi-task learning, resulting in additive significant improvements for SRL.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationFeature EngineeringGeneral ClassificationInformation RetrievalMulti-Task LearningNamed Entity Recognition (NER)Part-Of-Speech TaggingRelationRelation ClassificationSemantic Role LabelingSentenceSimilar Papers 제목 키워드 기반
Encoder-decoder based unified semantic role labeling with label-aware syntax
Currently the unified semantic role labeling (SRL) that achieves predicate identification and argument role labeling in an end-to-end manner has received growing interests. Recent works show that leveraging the syntax kn…
DecoderSemantic Role LabelingGeneralizing Natural Language Analysis through Span-relation Representations
Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures. In this paper, we prov…
Aspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)Constituency ParsingDependency Parsing+8Mastering the Explicit Opinion-role Interaction: Syntax-aided Neural Transition System for Unified Opinion Role Labeling
Unified opinion role labeling (ORL) aims to detect all possible opinion structures of 'opinion-holder-target' in one shot, given a text. The existing transition-based unified method, unfortunately, is subject to longer o…
Fine-Grained Opinion AnalysisPOLYGLOT: Multilingual Semantic Role Labeling with Unified Labels
Syntax Aware LSTM model for Semantic Role Labeling
In Semantic Role Labeling (SRL) task, the tree structured dependency relation is rich in syntax information, but it is not well handled by existing models. In this paper, we propose Syntax Aware Long Short Time Memory (S…
Feature EngineeringMachine TranslationmodelRelation+3