{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/computationally-efficient-ner-taggers-with","title":"Computationally Efficient NER Taggers with Combined Embeddings and Constrained Decoding","arxiv_id":"2001.01167","date":"2020-01-05","proceeding":null,"authors":["Brian Lester","Daniel Pressel","Amy Hemmeter","Sagnik Ray Choudhury"],"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 $786$\\% 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.","url_abs":"https://arxiv.org/abs/2001.01167v2","url_pdf":"https://arxiv.org/pdf/2001.01167v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"computationally-efficient-ner-taggers-with","repo_url":"https://github.com/dpressel/mead-baseline","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"cg","task_name":"NER"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"tag","task_name":"TAG"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[{"method_slug":"crf","method_name":"CRF"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}