Semi-supervised sequence tagging with bidirectional language models

Abstract

Pre-trained word embeddings learned from unlabeled text have become a standard component of neural network architectures for NLP tasks. However, in most cases, the recurrent network that operates on word-level representations to produce context sensitive representations is trained on relatively little labeled data. In this paper, we demonstrate a general… (More)
DOI: 10.18653/v1/P17-1161

Topics

8 Figures and Tables

Slides referencing similar topics