1 |
EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Delving Deeper into Cross-lingual Visual Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Improving Word Translation via Two-Stage Contrastive Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Multilingual and Cross-Lingual Intent Detection from Spoken Data ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Modelling Latent Translations for Cross-Lingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Prix-LM: Pretraining for Multilingual Knowledge Base Construction ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
On Cross-Lingual Retrieval with Multilingual Text Encoders ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
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. ... : CoNLL 2021 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2109.09237 https://arxiv.org/abs/2109.09237
|
|
BASE
|
|
Hide details
|
|
|
|