English

Computationally Efficient NER Taggers with Combined Embeddings and Constrained Decoding

Computation and Language 2021-03-25 v2

Abstract

Current State-of-the-Art models in Named Entity Recognition (NER) are neural models with a Conditional Random Field (CRF) as the final network layer, and pre-trained "contextual embeddings". The CRF layer is used to facilitate global coherence between labels, and the contextual embeddings provide a better representation of words in context. However, both of these improvements come at a high computational cost. In this work, we explore two simple techniques that substantially improve NER performance over a strong baseline with negligible cost. First, we use multiple pre-trained embeddings as word representations via concatenation. Second, we constrain the tagger, trained using a cross-entropy loss, during decoding to eliminate illegal transitions. While training a tagger on CoNLL 2003 we find a 786786\% speed-up over a contextual embeddings-based tagger without sacrificing strong performance. We also show that the concatenation technique works across multiple tasks and datasets. We analyze aspects of similarity and coverage between pre-trained embeddings and the dynamics of tag co-occurrence to explain why these techniques work. We provide an open source implementation of our tagger using these techniques in three popular deep learning frameworks --- TensorFlow, Pytorch, and DyNet.

Keywords

Cite

@article{arxiv.2001.01167,
  title  = {Computationally Efficient NER Taggers with Combined Embeddings and Constrained Decoding},
  author = {Brian Lester and Daniel Pressel and Amy Hemmeter and Sagnik Ray Choudhury},
  journal= {arXiv preprint arXiv:2001.01167},
  year   = {2021}
}

Comments

This paper has since been split into two. See arXiv:2009.14394 for the paper on Combined Embeddings and arXiv:2010.04362 for the paper on Constrained Decoding

R2 v1 2026-06-23T13:03:01.415Z