Augmented Natural Language for Generative Sequence Labeling

• DOI: 10.18653/v1/2020.emnlp-main.27
• Publication Date: 2020-11-29T14:51:46Z
• Authors: Ben Athiwaratkun; Cicero Nogueira d...; Jason Krone; Bing Xiang
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Computer Science - Computation and Language; Statistics - Machine Learning; 0202 electrical engineering, electronic engineering, information engineering; Machine Learning (stat.ML); 02 engineering and technology; Computation and Language (cs.CL); Machine Learning (cs.LG)

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 ($75.0\% \rightarrow 90.9\%$) and 1-shot ($70.4\% \rightarrow 81.0\%$) state-of-the-art results. Furthermore, our model generates large improvements ($46.27\% \rightarrow 63.83\%$) 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.<br/>To appear at EMNLP 2020<br/>