1 |
Improving Multilingual Translation by Representation and Gradient Regularization ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Discovering Representation Sprachbund For Multilingual Pre-Training ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Multi-Source Cross-Lingual Model Transfer: Learning What to Share ...
|
|
|
|
Abstract:
Modern NLP applications have enjoyed a great boost utilizing neural networks models. Such deep neural models, however, are not applicable to most human languages due to the lack of annotated training data for various NLP tasks. Cross-lingual transfer learning (CLTL) is a viable method for building NLP models for a low-resource target language by leveraging labeled data from other (source) languages. In this work, we focus on the multilingual transfer setting where training data in multiple source languages is leveraged to further boost target language performance. Unlike most existing methods that rely only on language-invariant features for CLTL, our approach coherently utilizes both language-invariant and language-specific features at instance level. Our model leverages adversarial networks to learn language-invariant features, and mixture-of-experts models to dynamically exploit the similarity between the target language and each individual source language. This enables our model to learn effectively what ... : ACL 2019 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://dx.doi.org/10.48550/arxiv.1810.03552 https://arxiv.org/abs/1810.03552
|
|
BASE
|
|
Hide details
|
|
4 |
Universal Neural Machine Translation for Extremely Low Resource Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Synthetic Data for Neural Machine Translation of Spoken-Dialects ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
A syntactified direct translation model with linear-time decoding
|
|
|
|
In: Hassan, Hany, Sima'an, Khalil and Way, Andy orcid:0000-0001-5736-5930 (2009) A syntactified direct translation model with linear-time decoding. In: EMNLP 2009 - Conference on Empirical Methods in Natural Language Processing, 6-7 August 2009, Singapore. (2009)
|
|
BASE
|
|
Show details
|
|
9 |
Lexical syntax for statistical machine translation
|
|
Hassan, Hany. - : Dublin City University. School of Computing, 2009
|
|
In: Hassan, Hany (2009) Lexical syntax for statistical machine translation. PhD thesis, Dublin City University. (2009)
|
|
BASE
|
|
Show details
|
|
10 |
Lexicalized semi-incremental dependency parsing
|
|
|
|
In: Hassan, Hany, Sima'an, Khalil and Way, Andy orcid:0000-0001-5736-5930 (2009) Lexicalized semi-incremental dependency parsing. In: RANLP-2009 - Recent Advances in Natural Language Processing, 14-16 September 2009, Borovets, Bulgaria. (2009)
|
|
BASE
|
|
Show details
|
|
12 |
Exploiting alignment techniques in MATREX: the DCU machine translation system for IWSLT 2008
|
|
|
|
In: Ma, Yanjun, Tinsley, John, Hassan, Hany, Du, Jinhua orcid:0000-0002-3267-4881 and Way, Andy orcid:0000-0001-5736-5930 (2008) Exploiting alignment techniques in MATREX: the DCU machine translation system for IWSLT 2008. In: IWSLT 2008 - International Workshop on Spoken Language Translation, 20-21 October 2008, Hawaii, USA. (2008)
|
|
BASE
|
|
Show details
|
|
13 |
Supertagged phrase-based statistical machine translation
|
|
|
|
In: Hassan, Hany, Sima'an, Khalil and Way, Andy orcid:0000-0001-5736-5930 (2007) Supertagged phrase-based statistical machine translation. In: ACL 2007 - 45th Annual Meeting of the Association for Computational Linguistics, 25-27 June 2007, Prague, Czech Republic. (2007)
|
|
BASE
|
|
Show details
|
|
|
|