DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 35

1
DALC: the Dutch Abusive Language Corpus ...
BASE
Show details
2
Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer ...
BASE
Show details
3
Adapting Monolingual Models: Data can be Scarce when Language Similarity is High ...
Abstract: For many (minority) languages, the resources needed to train large models are not available. We investigate the performance of zero-shot transfer learning with as little data as possible, and the influence of language similarity in this process. We retrain the lexical layers of four BERT-based models using data from two low-resource target language varieties, while the Transformer layers are independently fine-tuned on a POS-tagging task in the model's source language. By combining the new lexical layers and fine-tuned Transformer layers, we achieve high task performance for both target languages. With high language similarity, 10MB of data appears sufficient to achieve substantial monolingual transfer performance. Monolingual BERT-based models generally achieve higher downstream task performance after retraining the lexical layer than multilingual BERT, even when the target language is included in the multilingual model. ... : Findings of ACL 2021 Camera Ready ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://dx.doi.org/10.48550/arxiv.2105.02855
https://arxiv.org/abs/2105.02855
BASE
Hide details
4
Adapting Monolingual Models: Data can be Scarce when Language Similarity is High ...
BASE
Show details
5
As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages ...
BASE
Show details
6
Teaching NLP with Bracelets and Restaurant Menus:An Interactive Workshop for Italian Students
Pannitto, Ludovica; Busso, Lucia; Combei, Claudia Roberta. - : Association for Computational Linguistics, 2021
BASE
Show details
7
What's so special about BERT's layers? A closer look at the NLP pipeline in monolingual and multilingual models ...
BASE
Show details
8
Matching Theory and Data with Personal-ITY: What a Corpus of Italian YouTube Comments Reveals About Personality ...
BASE
Show details
9
Unmasking Contextual Stereotypes: Measuring and Mitigating BERT'S Gender Bias ...
BASE
Show details
10
As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages ...
de Vries, Wietse; Nissim, Malvina. - : arXiv, 2020
BASE
Show details
11
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
12
Sentiment Polarity Classification at EVALITA: Lessons Learned and Open Challenges
BASE
Show details
13
Learning Neural Word Salience Scores.
Gargett, Andrew; Bollegala, Danushka; Samardzhiev, Krasen. - : Association for Computational Linguistics, 2018
BASE
Show details
14
-io Nouns through the Ages. Analysing Latin Morphological Productivity with Lemlat
Litta, Eleonora (orcid:0000-0002-0499-997X); Passarotti, Marco (orcid:0000-0002-9806-7187); Budassi, Marco. - : aAccademia University Press, 2017. : country:ITA, 2017. : place:ROMA -- ITA, 2017
BASE
Show details
15
EVALITA Goes Social: Tasks, Data, and Community at the 2016 Edition
Cutugno, Francesco; Sprugnoli, Rachele (orcid:0000-0001-6861-5595); Nissim, Malvina. - 2017
BASE
Show details
16
Overview of the Evalita 2016 SENTIment POLarity Classification Task
In: Proceedings of Third Italian Conference on Computational Linguistics (CLiC-it 2016) & Fifth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2016) ; https://hal.inria.fr/hal-01414731 ; Proceedings of Third Italian Conference on Computational Linguistics (CLiC-it 2016) & Fifth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2016), Dec 2016, Naples, Italy (2016)
BASE
Show details
17
Overview of the Evalita 2016 Sentiment Polarity Classification Task
Barbieri, Francesco; Basile, Valerio; Croce, Danilo. - : CEUR-WS, 2016. : country:DEU, 2016. : place:Aachen, 2016
BASE
Show details
18
EVALITA 2016: Overview of the 5th evaluation campaign of natural language processing and speech tools for Italian
Basile, Pierpaolo; Cutugno, Franco; Nissim, Malvina. - : CEUR-WS, 2016. : country:DEU, 2016. : place:Aachen, 2016
BASE
Show details
19
Deep Tweets: from Entity Linking to Sentiment Analysis
In: Proceedings of the Italian Computational Linguistics Conference (CLiC-it 2015) ; https://hal.inria.fr/hal-01342435 ; Proceedings of the Italian Computational Linguistics Conference (CLiC-it 2015), Dec 2015, Trento, Italy (2015)
BASE
Show details
20
Overview of the Evalita 2014 SENTIment POLarity Classification Task
In: Proceedings of the 4th evaluation campaign of Natural Language Processing and Speech tools for Italian (EVALITA'14) ; https://hal.inria.fr/hal-01228925 ; Proceedings of the 4th evaluation campaign of Natural Language Processing and Speech tools for Italian (EVALITA'14), 2014, Pisa, Italy. ⟨10.12871/clicit201429⟩ (2014)
BASE
Show details

Page: 1 2

Catalogues
0
0
4
0
0
0
0
Bibliographies
6
0
0
0
0
0
0
0
1
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
26
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern