Matthew Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, & Luke Zettlemoyer (2018)
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), 2227-2237.
DOI: https://doi.org/10.18653/v1/n18-1202
Abstract. Introduces ELMo, which generates contextualised word representations from a bidirectional LSTM language model. ELMo embeddings, which depend on the surrounding sentence, dramatically improved performance across many NLP benchmarks.
Tags: embeddings elmo contextualised nlp