Semi-supervised Relation Extraction via Data Augmentation and Consistency-training
Due to the semantic complexity of the Relation extraction (RE) task, obtaining high-quality human labelled data is an expensive and noisy process. To improve the sample efficiency of the models, semi-supervised learning (SSL) methods aim to leverage unlabelled data in addition to learning from limited labelled data points. Recently, strong data augmentation combined with consistency-based semi-supervised learning methods have advanced the state of the art in several SSL tasks. However, adapting these methods to the RE task has been challenging due to the difficulty of data augmentation for RE. In this work, we leverage the recent advances in controlled text generation to perform high quality data augmentation for the RE task. We further introduce small but significant changes to model architecture that allows for generation of more training data by interpolating different data points in their latent space. These data augmentations along with consistency training result in very competitive results for semi-supervised relation extraction on four benchmark datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationRelationRelation ExtractionText GenerationSimilar Papers 제목 키워드 기반
Jointprop: Joint Semi-supervised Learning for Entity and Relation Extraction with Heterogeneous Graph-based Propagation
Semi-supervised learning has been an important approach to address challenges in extracting entities and relations from limited data. However, current semi-supervised works handle the two tasks (i.e., Named Entity Recogn…
named-entity-recognitionNamed Entity RecognitionNERRelation+1The AI2 system at SemEval-2017 Task 10 (ScienceIE): semi-supervised end-to-end entity and relation extraction
This paper describes our submission for the ScienceIE shared task (SemEval- 2017 Task 10) on entity and relation extraction from scientific papers. Our model is based on the end-to-end relation extraction model of Miwa a…
Dependency ParsingPart-Of-Speech TaggingRelationRelation ExtractionExploring Semi-supervised Variational Autoencoders for Biomedical Relation Extraction
The biomedical literature provides a rich source of knowledge such as protein-protein interactions (PPIs), drug-drug interactions (DDIs) and chemical-protein interactions (CPIs). Biomedical relation extraction aims to au…
DecoderRelationRelation ExtractionUnsupervised Data Augmentation for Aspect Based Sentiment Analysis
Recent approaches to Aspect-based Sentiment Analysis (ABSA) take a co-extraction approach to this span-level classification task, performing the subtasks of aspect term extraction (ATE) and aspect sentiment classificatio…
Aspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)ClassificationData Augmentation+5Adversarial Learning for Supervised and Semi-supervised Relation Extraction in Biomedical Literature
Adversarial training is a technique of improving model performance by involving adversarial examples in the training process. In this paper, we investigate adversarial training with multiple adversarial examples to benef…
BenchmarkingRelationRelation Extraction