# Semi-supervised sequence tagging with bidirectional language models

## TL;DR

This paper introduces a semi-supervised method that leverages pre-trained bidirectional language models to enhance sequence labeling tasks like NER and chunking, achieving state-of-the-art results with less labeled data.

## Contribution

It presents a novel semi-supervised approach for incorporating pre-trained context embeddings from bidirectional language models into NLP systems for sequence tagging.

## Key findings

- Achieved state-of-the-art results on NER and chunking datasets.
- Surpassed previous systems using transfer learning and gazetteers.
- Effective use of unlabeled data improves sequence labeling performance.

## 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 semi-supervised approach for adding pre- trained context embeddings from bidirectional language models to NLP systems and apply it to sequence labeling tasks. We evaluate our model on two standard datasets for named entity recognition (NER) and chunking, and in both cases achieve state of the art results, surpassing previous systems that use other forms of transfer or joint learning with additional labeled data and task specific gazetteers.