Dynamic Contextualized Word Embeddings

Valentin Hofmann; Janet Pierrehumbert; Hinrich Schütze

ACL 2021long83 citations

Dynamic Contextualized Word Embeddings

Valentin Hofmann, Janet Pierrehumbert, Hinrich Schütze

Abstract

Static word embeddings that represent words by a single vector cannot capture the variability of word meaning in different linguistic and extralinguistic contexts. Building on prior work on contextualized and dynamic word embeddings, we introduce dynamic contextualized word embeddings that represent words as a function of both linguistic and extralinguistic context. Based on a pretrained language model (PLM), dynamic contextualized word embeddings model time and social space jointly, which makes them attractive for a range of NLP tasks involving semantic variability. We highlight potential application scenarios by means of qualitative and quantitative analyses on four English datasets.

BibTeX

@inproceedings{hofmann-etal-2021-dynamic,
    title = "Dynamic Contextualized Word Embeddings",
    author = {Hofmann, Valentin  and
      Pierrehumbert, Janet  and
      Sch{\"u}tze, Hinrich},
    editor = "Zong, Chengqing  and
      Xia, Fei  and
      Li, Wenjie  and
      Navigli, Roberto",
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.acl-long.542/",
    doi = "10.18653/v1/2021.acl-long.542",
    pages = "6970--6984"
}