1 |
AraWEAT: Multidimensional Analysis of Biases in Arabic Word Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Orthogonal Language and Task Adapters in Zero-Shot Cross-Lingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
XHate-999: Analyzing and Detecting Abusive Language Across Domains and Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformers ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformers ...
|
|
|
|
Abstract:
Massively multilingual transformers pretrained with language modeling objectives (e.g., mBERT, XLM-R) have become a de facto default transfer paradigm for zero-shot cross-lingual transfer in NLP, offering unmatched transfer performance. Current downstream evaluations, however, verify their efficacy predominantly in transfer settings involving languages with sufficient amounts of pretraining data, and with lexically and typologically close languages. In this work, we analyze their limitations and show that cross-lingual transfer via massively multilingual transformers, much like transfer via cross-lingual word embeddings, is substantially less effective in resource-lean scenarios and for distant languages. Our experiments, encompassing three lower-level tasks (POS tagging, dependency parsing, NER), as well as two high-level semantic tasks (NLI, QA), empirically correlate transfer performance with linguistic similarity between the source and target languages, but also with the size of pretraining corpora of ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2005.00633 https://dx.doi.org/10.48550/arxiv.2005.00633
|
|
BASE
|
|
Hide details
|
|
9 |
Verb Knowledge Injection for Multilingual Event Processing ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Probing Pretrained Language Models for Lexical Semantics ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
SemEval-2020 Task 2: Predicting Multilingual and Cross-Lingual (Graded) Lexical Entailment ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
SemEval-2020 Task 2: Predicting Multilingual and Cross-Lingual (Graded) Lexical Entailment ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Non-Linear Instance-Based Cross-Lingual Mapping for Non-Isomorphic Embedding Spaces ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Probing Pretrained Language Models for Lexical Semantics ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Classification-Based Self-Learning for Weakly Supervised Bilingual Lexicon Induction ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Improving Bilingual Lexicon Induction with Unsupervised Post-Processing of Monolingual Word Vector Spaces ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Improving Bilingual Lexicon Induction with Unsupervised Post-Processing of Monolingual Word Vector Spaces
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity
|
|
Lauscher, Anne; Vulic, Ivan; Ponti, Edoardo. - : International Committee on Computational Linguistics, 2020. : https://www.aclweb.org/anthology/2020.coling-main.118, 2020. : Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020), 2020
|
|
BASE
|
|
Show details
|
|
|
|