DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 34

1
Delving Deeper into Cross-lingual Visual Question Answering ...
BASE
Show details
2
Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation ...
BASE
Show details
3
Improving Word Translation via Two-Stage Contrastive Learning ...
BASE
Show details
4
Towards Zero-shot Language Modeling ...
BASE
Show details
5
Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems ...
BASE
Show details
6
Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking ...
BASE
Show details
7
Combining Deep Generative Models and Multi-lingual Pretraining for Semi-supervised Document Classification ...
Zhu, Yi; Shareghi, Ehsan; Li, Yingzhen. - : arXiv, 2021
BASE
Show details
8
MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models ...
BASE
Show details
9
Context vs Target Word: Quantifying Biases in Lexical Semantic Datasets ...
BASE
Show details
10
AM2iCo: Evaluating Word Meaning in Context across Low-Resource Languages with Adversarial Examples ...
BASE
Show details
11
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders ...
Abstract: Pretrained Masked Language Models (MLMs) have revolutionised NLP in recent years. However, previous work has indicated that off-the-shelf MLMs are not effective as universal lexical or sentence encoders without further task-specific fine-tuning on NLI, sentence similarity, or paraphrasing tasks using annotated task data. In this work, we demonstrate that it is possible to turn MLMs into effective universal lexical and sentence encoders even without any additional data and without any supervision. We propose an extremely simple, fast and effective contrastive learning technique, termed Mirror-BERT, which converts MLMs (e.g., BERT and RoBERTa) into such encoders in 20-30 seconds without any additional external knowledge. Mirror-BERT relies on fully identical or slightly modified string pairs as positive (i.e., synonymous) fine-tuning examples, and aims to maximise their similarity during identity fine-tuning. We report huge gains over off-the-shelf MLMs with Mirror-BERT in both lexical-level and sentence-level ... : EMNLP 2021 camera-ready version ...
Keyword: Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
URL: https://arxiv.org/abs/2104.08027
https://dx.doi.org/10.48550/arxiv.2104.08027
BASE
Hide details
12
XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning ...
BASE
Show details
13
Emergent Communication Pretraining for Few-Shot Machine Translation ...
BASE
Show details
14
A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters ...
BASE
Show details
15
Verb Knowledge Injection for Multilingual Event Processing ...
BASE
Show details
16
Multi-SimLex: A Large-Scale Evaluation of Multilingual and Cross-Lingual Lexical Semantic Similarity ...
BASE
Show details
17
Probing Pretrained Language Models for Lexical Semantics ...
BASE
Show details
18
The Secret is in the Spectra: Predicting Cross-lingual Task Performance with Spectral Similarity Measures ...
BASE
Show details
19
Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity ...
BASE
Show details
20
Do We Really Need Fully Unsupervised Cross-Lingual Embeddings? ...
BASE
Show details

Page: 1 2

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
34
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern