A Brief Overview of Universal Sentence Representation Methods: A Linguistic View
ACM Computing Surveys · 31.03.2023 · 55 (3) · 1-42
DOI: 10.1145/3482853 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 26.03.2022. Verfasst von Ruiqi Li und 2 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 164 Literaturangaben. Gefördert von: NSFC, NSF of Hunan Province, Science and Technology Innovation Program of Hunan Province.
Abstract (Originalsprache)
How to transfer the semantic information in a sentence to a computable numerical embedding form is a fundamental problem in natural language processing. An informative universal sentence embedding can greatly promote subsequent natural language processing tasks. However, unlike universal word embeddings, a widely accepted general-purpose sentence embedding technique has not been developed. This survey summarizes the current universal sentence-embedding methods, categorizes them into four groups from a linguistic view, and ultimately analyzes their reported performance. Sentence embeddings trained from words in a bottom-up manner are observed to have different, nearly opposite, performance patterns in downstream tasks compared to those trained from logical relationships between sentences. By comparing differences of training schemes in and between groups, we analyze possible essential reasons for different performance patterns. We additionally collect incentive strategies handling sentences from other models and propose potentially inspiring future research directions.
Förderung
- NSFC
- NSF of Hunan Province
- Science and Technology Innovation Program of Hunan Province
- European Research Council
Zitieren
APA
Li, R., Zhao, X., & Moens, M. (2023). A Brief Overview of Universal Sentence Representation Methods: A Linguistic View. ACM Computing Surveys, 55(3), 1-42. https://doi.org/10.1145/3482853
Vancouver
Li R, Zhao X, Moens M. A Brief Overview of Universal Sentence Representation Methods: A Linguistic View. ACM Computing Surveys. 2023;55(3):1-42. doi:10.1145/3482853
BibTeX
@article{Li2023,
author = {Li, Ruiqi and Zhao, Xiang and Moens, Marie-Francine},
title = {A Brief Overview of Universal Sentence Representation Methods: A Linguistic View},
journal = {ACM Computing Surveys},
year = {2023},
volume = {55},
number = {3},
pages = {1--42},
doi = {10.1145/3482853}
}
EUVIMED