What Do You Learn From Context? Probing For Sentence Structure In Contextualized Word Representations
Tenney Ian, Xia Patrick, Chen Berlin, Wang Alex, Poliak Adam, Mccoy R Thomas, Kim Najoung, Van Durme Benjamin, Bowman Samuel R., Das Dipanjan, Pavlick Ellie. Arxiv 2019
[Paper]
Contextualized representation models such as ELMo (Peters et al., 2018a) and BERT (Devlin et al., 2018) have recently achieved state-of-the-art results on a diverse array of downstream NLP tasks. Building on recent token-level probing work, we introduce a novel edge probing task design and construct a broad suite of sub-sentence tasks derived from the traditional structured NLP pipeline. We probe word-level contextual representations from four recent models and investigate how they encode sentence structure across a range of syntactic, semantic, local, and long-range phenomena. We find that existing models trained on language modeling and translation produce strong representations for syntactic phenomena, but only offer comparably small improvements on semantic tasks over a non-contextual baseline.
Similar Work