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 ...
|
|
|
|
BASE
|
|
Show 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 ...
|
|
|
|
Abstract:
Large generative language models have been very successful for English, but other languages lag behind, in part due to data and computational limitations. We propose a method that may overcome these problems by adapting existing pre-trained models to new languages. Specifically, we describe the adaptation of English GPT-2 to Italian and Dutch by retraining lexical embeddings without tuning the Transformer layers. As a result, we obtain lexical embeddings for Italian and Dutch that are aligned with the original English lexical embeddings. Additionally, we scale up complexity by transforming relearned lexical embeddings of GPT-2 small to the GPT-2 medium embedding space. This method minimises the amount of training and prevents losing information during adaptation that was learned by GPT-2. English GPT-2 models with relearned lexical embeddings can generate realistic sentences in Italian and Dutch. Though on average these sentences are still identifiable as artificial by humans, they are assessed on par with ... : Findings of ACL 2021 Camera Ready ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2012.05628 https://dx.doi.org/10.48550/arxiv.2012.05628
|
|
BASE
|
|
Hide 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
|
|
|
|