Amazing technological breakthrough possible @S-Logix

Office Address

  • #5, First Floor, 4th Street Dr. Subbarayan Nagar Kodambakkam, Chennai-600 024 Landmark : Samiyar Madam
  • +91- 81240 01111

Social List

Deep contextualized word representations - 2018

Deep Contextualized Word Representations

Research Paper on Deep Contextualized Word Representations

Research Area:  Machine Learning


We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i.e., to model polysemy). Our word vectors are learned functions of the internal states of a deep bidirectional language model (biLM), which is pre-trained on a large text corpus. We show that these representations can be easily added to existing models and significantly improve the state of the art across six challenging NLP problems, including question answering, textual entailment and sentiment analysis. We also present an analysis showing that exposing the deep internals of the pre-trained network is crucial, allowing downstream models to mix different types of semi-supervision signals.

Word Representations
Machine Learning
Deep Learning

Author(s) Name:  Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke Zettlemoyer

Journal name:  

Conferrence name:  Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

Publisher name:  Association for Computational Linguistics

DOI:  10.18653/v1/N18-1202

Volume Information:  pp 2227–2237