DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4
Hits 1 – 20 of 67

1
Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation ...
BASE
Show details
2
Improving Word Translation via Two-Stage Contrastive Learning ...
BASE
Show details
3
Towards Zero-shot Language Modeling ...
BASE
Show details
4
Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems ...
BASE
Show details
5
Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking ...
BASE
Show details
6
MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models ...
BASE
Show details
7
Parameter space factorization for zero-shot learning across tasks and languages ...
BASE
Show details
8
MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models ...
Liu, Qianchu; Liu, Fangyu; Collier, Nigel; Korhonen, Anna; Vulić, Ivan. - : Apollo - University of Cambridge Repository, 2021
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
9
Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking ...
BASE
Show details
10
MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models ...
BASE
Show details
11
AM2iCo: Evaluating Word Meaning in Context across Low-Resource Languages with Adversarial Examples ...
BASE
Show details
12
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders ...
BASE
Show details
13
Parameter space factorization for zero-shot learning across tasks and languages
In: Transactions of the Association for Computational Linguistics, 9 (2021)
BASE
Show details
14
AM2iCo: Evaluating Word Meaning in Context across Low-Resource Languages with Adversarial Examples ...
BASE
Show details
15
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders ...
BASE
Show details
16
LexFit: Lexical Fine-Tuning of Pretrained Language Models ...
BASE
Show details
17
Verb Knowledge Injection for Multilingual Event Processing ...
BASE
Show details
18
A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters ...
BASE
Show details
19
XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning ...
BASE
Show details
20
Emergent Communication Pretraining for Few-Shot Machine Translation ...
BASE
Show details

Page: 1 2 3 4

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
67
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern