English

Augmented Natural Language for Generative Sequence Labeling

Computation and Language 2020-09-29 v1 Machine Learning Machine Learning

Abstract

We propose a generative framework for joint sequence labeling and sentence-level classification. Our model performs multiple sequence labeling tasks at once using a single, shared natural language output space. Unlike prior discriminative methods, our model naturally incorporates label semantics and shares knowledge across tasks. Our framework is general purpose, performing well on few-shot, low-resource, and high-resource tasks. We demonstrate these advantages on popular named entity recognition, slot labeling, and intent classification benchmarks. We set a new state-of-the-art for few-shot slot labeling, improving substantially upon the previous 5-shot (75.0%90.9%75.0\% \rightarrow 90.9\%) and 1-shot (70.4%81.0%70.4\% \rightarrow 81.0\%) state-of-the-art results. Furthermore, our model generates large improvements (46.27%63.83%46.27\% \rightarrow 63.83\%) in low-resource slot labeling over a BERT baseline by incorporating label semantics. We also maintain competitive results on high-resource tasks, performing within two points of the state-of-the-art on all tasks and setting a new state-of-the-art on the SNIPS dataset.

Keywords

Cite

@article{arxiv.2009.13272,
  title  = {Augmented Natural Language for Generative Sequence Labeling},
  author = {Ben Athiwaratkun and Cicero Nogueira dos Santos and Jason Krone and Bing Xiang},
  journal= {arXiv preprint arXiv:2009.13272},
  year   = {2020}
}

Comments

To appear at EMNLP 2020

R2 v1 2026-06-23T18:50:42.716Z