1 |
IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Improving Word Translation via Two-Stage Contrastive Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Prix-LM: Pretraining for Multilingual Knowledge Base Construction ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models ...
|
|
|
|
Abstract:
Recent work indicated that pretrained language models (PLMs) such as BERT and RoBERTa can be transformed into effective sentence and word encoders even via simple self-supervised techniques. Inspired by this line of work, in this paper we propose a fully unsupervised approach to improving word-in-context (WiC) representations in PLMs, achieved via a simple and efficient WiC-targeted fine-tuning procedure: MirrorWiC. The proposed method leverages only raw texts sampled from Wikipedia, assuming no sense-annotated data, and learns context-aware word representations within a standard contrastive learning setup. We experiment with a series of standard and comprehensive WiC benchmarks across multiple languages. Our proposed fully unsupervised MirrorWiC models obtain substantial gains over off-the-shelf PLMs across all monolingual, multilingual and cross-lingual setups. Moreover, on some standard WiC benchmarks, MirrorWiC is even on-par with supervised models fine-tuned with in-task data and sense labels. ...
|
|
Keyword:
cs.CL
|
|
URL: https://dx.doi.org/10.17863/cam.78495 https://www.repository.cam.ac.uk/handle/1810/331050
|
|
BASE
|
|
Hide details
|
|
7 |
Visually Grounded Reasoning across Languages and Cultures ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Visually Grounded Reasoning across Languages and Cultures ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Visually Grounded Reasoning across Languages and Cultures ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Self-Alignment Pretraining for Biomedical Entity Representations
|
|
Liu, Fangyu; Shareghi, Ehsan; Meng, Zaiqiao. - : Association for Computational Linguistics, 2021. : Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021
|
|
BASE
|
|
Show details
|
|
16 |
Upgrading the Newsroom: An Automated Image Selection System for News Articles ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Upgrading the Newsroom: An Automated Image Selection System for News Articles
|
|
|
|
In: http://infoscience.epfl.ch/record/280322 (2020)
|
|
BASE
|
|
Show details
|
|
|
|