1 |
Combining Static and Contextualised Multilingual Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Do Multilingual Language Models Capture Differing Moral Norms? ...
|
|
|
|
Abstract:
Massively multilingual sentence representations are trained on large corpora of uncurated data, with a very imbalanced proportion of languages included in the training. This may cause the models to grasp cultural values including moral judgments from the high-resource languages and impose them on the low-resource languages. The lack of data in certain languages can also lead to developing random and thus potentially harmful beliefs. Both these issues can negatively influence zero-shot cross-lingual model transfer and potentially lead to harmful outcomes. Therefore, we aim to (1) detect and quantify these issues by comparing different models in different languages, (2) develop methods for improving undesirable properties of the models. Our initial experiments using the multilingual model XLM-R show that indeed multilingual LMs capture moral norms, even with potentially higher human-agreement than monolingual ones. However, it is not yet clear to what extent these moral norms differ between languages. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2203.09904 https://dx.doi.org/10.48550/arxiv.2203.09904
|
|
BASE
|
|
Hide details
|
|
3 |
Modeling Target-Side Morphology in Neural Machine Translation: A Comparison of Strategies ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Pushing the right buttons: adversarial evaluation of quality estimation
|
|
|
|
In: Proceedings of the Sixth Conference on Machine Translation ; 625 ; 638 (2022)
|
|
BASE
|
|
Show details
|
|
5 |
Do not neglect related languages: The case of low-resource Occitan cross-lingual word embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Anchor-based Bilingual Word Embeddings for Low-Resource Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Improving Machine Translation of Rare and Unseen Word Senses ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Combining Word Embeddings with Bilingual Orthography Embeddings for Bilingual Dictionary Induction ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Combining Word Embeddings with Bilingual Orthography Embeddings for Bilingual Dictionary Induction
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Pragmatic information in translation: a corpus-based study of tense and mood in English and German ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
ContraCAT: Contrastive Coreference Analytical Templates for Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Anchor-based Bilingual Word Embeddings for Low-Resource Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
On the Language Neutrality of Pre-trained Multilingual Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Embedding Learning Through Multilingual Concept Induction ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Embedding Learning Through Multilingual Concept Induction ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|