Paper: Deep contextualized word representations
Link: https://arxiv.org/abs/1802.05365 Authors: Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke Zettlemoyer
Code: https://bit.ly/3xpHNAI
Note - Since this is a relatively old paper, all the performance comparisons and state-of-the-art claims mentioned below should only be considered for the models at the time the paper was published.
What? The paper proposes a new type of deep contextualized word representation that helps to effectively capture the syntactic and semantic characteristics of the word along with the linguistic context of the word.