Unsupervised Paraphrasing Consistency Training for Low Resource Named Entity Recognition
Unsupervised consistency training is a way of semi-supervised learning that encourages consistency in model predictions between the original and augmented data. For Named Entity Recognition (NER), existing approaches augment the input sequence with token replacement, assuming annotations on the replaced positions unchanged. In this paper, we explore the use of paraphrasing as a more principled data augmentation scheme for NER unsupervised consistency training. Specifically, we convert Conditional Random Field (CRF) into a multi-label classification module and encourage consistency on the entity appearance between the original and paraphrased sequences. Experiments show that our method is especially effective when annotations are limited.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationLow Resource Named Entity RecognitionMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERSimilar Papers 제목 키워드 기반
ProtAugment: Intent Detection Meta-Learning through Unsupervised Diverse Paraphrasing
Recent research considers few-shot intent detection as a meta-learning problem: the model is learning to learn from a consecutive set of small tasks named episodes. In this work, we propose ProtAugment, a meta-learning a…
DiversityIntent DetectionLanguage ModelingLanguage Modelling+1ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning
Recent research considers few-shot intent detection as a meta-learning problem: the model is learning to learn from a consecutive set of small tasks named episodes. In this work, we propose ProtAugment, a meta-learning a…
DiversityIntent DetectionLanguage ModelingLanguage Modelling+1Unsupervised Paraphrasing of Multiword Expressions
We propose an unsupervised approach to paraphrasing multiword expressions (MWEs) in context. Our model employs only monolingual corpus data and pre-trained language models (without fine-tuning), and does not make use of …
text similarityLearning to Adapt to Low-Resource Paraphrase Generation
Paraphrase generation is a longstanding NLP task and achieves great success with the aid of large corpora. However, transferring a paraphrasing model to another domain encounters the problem of domain shifting especially…
Meta-LearningParaphrase GenerationUnsupervised Paraphrasing without Translation
Paraphrasing exemplifies the ability to abstract semantic content from surface forms. Recent work on automatic paraphrasing is dominated by methods leveraging Machine Translation (MT) as an intermediate step. This contra…
Machine TranslationParaphrase IdentificationTranslation