BIP! Finder - Dynamic Contextualized Word Embeddings

2021 • Dynamic Contextualized Word Embeddings

Authors: Hofmann, V; Pierrehumbert, JB; Schütze, H

Venue: 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)

Type: Publication

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 involvin... (read more)

Topics: Linguistics Natural language processing Artificial intelligence

DOI: 10.18653/v1/2021.acl-long.542

BIP! social metrics: 0 14
External links: Crossref OpenAIRE

Found 2 versions BibTex PDF

Topic-specific impact indicators

Popularity:
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
Influence:
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
Citation Count:
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
Impulse:
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.