2 |
IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Adapting Monolingual Models: Data can be Scarce when Language Similarity is High ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Generic resources are what you need: Style transfer tasks without task-specific parallel training data ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Adapting Monolingual Models: Data can be Scarce when Language Similarity is High ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Teaching NLP with Bracelets and Restaurant Menus: An Interactive Workshop for Italian Students ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Teaching NLP with Bracelets and Restaurant Menus:An Interactive Workshop for Italian Students
|
|
|
|
BASE
|
|
Show details
|
|
12 |
What's so special about BERT's layers? A closer look at the NLP pipeline in monolingual and multilingual models ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Personal-ITY: A Novel YouTube-based Corpus for Personality Prediction in Italian ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Datasets and Models for Authorship Attribution on Italian Personal Writings ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias ...
|
|
|
|
Abstract:
Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems. Since a variety of biases have previously been found in standard word embeddings, it is crucial to assess biases encoded in their replacements as well. Focusing on BERT (Devlin et al., 2018), we measure gender bias by studying associations between gender-denoting target words and names of professions in English and German, comparing the findings with real-world workforce statistics. We mitigate bias by fine-tuning BERT on the GAP corpus (Webster et al., 2018), after applying Counterfactual Data Substitution (CDS) (Maudslay et al., 2019). We show that our method of measuring bias is appropriate for languages such as English, but not for languages with a rich morphology and gender-marking, such as German. Our results highlight the importance of investigating bias and mitigation techniques cross-linguistically, especially in view of the current emphasis on large-scale, ... : 10 pages, 4 figures, to appear in Proceedings of the 2nd Workshop on Gender Bias in Natural Language Processing at COLING 2020 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2010.14534 https://dx.doi.org/10.48550/arxiv.2010.14534
|
|
BASE
|
|
Hide details
|
|
16 |
Matching Theory and Data with Personal-ITY: What a Corpus of Italian YouTube Comments Reveals About Personality ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Unmasking Contextual Stereotypes: Measuring and Mitigating BERT'S Gender Bias ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Fair Is Better than Sensational: Man Is to Doctor as Woman Is to Doctor
|
|
|
|
In: Computational Linguistics, Vol 46, Iss 2, Pp 487-497 (2020) (2020)
|
|
BASE
|
|
Show details
|
|
|
|