Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Marc Dymetman"'
The Internet gives us access to a wealth of information in languages we don't understand. The investigation of automated or semi-automated approaches to translation has become a thriving research field with enormous commercial potential. This volume
Autor:
Claude Roux, Ioan Calapodescu, Jean-Luc Meunier, Alexandre Berard, Vassilina Nikoulina, Marc Dymetman
Publikováno v:
NGT@EMNLP-IJCNLP
We share a French-English parallel corpus of Foursquare restaurant reviews (https://europe.naverlabs.com/research/natural-language-processing/machine-translation-of-restaurant-reviews), and define a new task to encourage research on Neural Machine Tr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::231293763925a7093bc87fd0c3b094af
http://arxiv.org/abs/1910.14589
http://arxiv.org/abs/1910.14589
Publikováno v:
CoNLL
Standard autoregressive seq2seq models are easily trained by max-likelihood, but tend to show poor results under small-data conditions. We introduce a class of seq2seq models, GAMs (Global Autoregressive Models), which combine an autoregressive compo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::68d72a968353a30070871f0db001a252
http://arxiv.org/abs/1909.07063
http://arxiv.org/abs/1909.07063
Publikováno v:
INLG
This paper describes our submission to the E2E NLG Challenge. Recently, neural seq2seq approaches have become mainstream in NLG, often resorting to pre- (respectively post-) processing delexicalization (relexicalization) steps at the word-level to ha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc2234c23c1eed9b1f9c5fb5f2beb676
http://arxiv.org/abs/1811.05826
http://arxiv.org/abs/1811.05826
Publikováno v:
wenty-sixth International Joint Conference on Artificial Intelligence (IJCAI-17)
wenty-sixth International Joint Conference on Artificial Intelligence (IJCAI-17), Aug 2017, Melbourne, Australia. pp.4186-4192, ⟨10.24963/ijcai.2017/585⟩
IJCAI
wenty-sixth International Joint Conference on Artificial Intelligence (IJCAI-17), Aug 2017, Melbourne, Australia. pp.4186-4192, ⟨10.24963/ijcai.2017/585⟩
IJCAI
Seq2seq models based on Recurrent Neural Networks (RNNs) have recently received a lot of attention in the domain of Semantic Parsing. While in principle they can be trained directly on pairs (natural language utterances, logical forms), their perform
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4f96e32614da7e36f9bb723914206d07
http://arxiv.org/abs/1809.07721
http://arxiv.org/abs/1809.07721
Autor:
Marc Dymetman, Shubham Agarwal
Publikováno v:
SIGDIAL Conference
We train a char2char model on the E2E NLG Challenge data, by exploiting “out-of-the-box” the recently released tfseq2seq framework, using some of the standard options offered by this tool. With minimal effort, and in particular without delexicali
Publikováno v:
Annual meeting of the Association for Computational Linguistics (ACL)
Annual meeting of the Association for Computational Linguistics (ACL), Aug 2016, Berlin, Germany. pp.1341-1350, ⟨10.18653/v1/P16-1127⟩
ACL (1)
Annual meeting of the Association for Computational Linguistics (ACL), Aug 2016, Berlin, Germany. pp.1341-1350, ⟨10.18653/v1/P16-1127⟩
ACL (1)
International audience; We propose an approach for semantic parsing that uses a recurrent neural network to map a natural language question into a logical form representation of a KB query. Building on recent work by (Wang et al., 2015), the interpre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c8e99d0f3d6703d4a8290156590905af
https://hal.inria.fr/hal-01623762/document
https://hal.inria.fr/hal-01623762/document
Publikováno v:
Rep4NLP@ACL
We introduce an LSTM-based method for dynamically integrating several wordprediction experts to obtain a conditional language model which can be good simultaneously at several subtasks. We illustrate this general approach with an application to dialo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f83e011d2ce54dc89a91df175c6bbecf
Publikováno v:
EMNLP
We restate the classical logical notion of generation/parsing reversibility in terms of feasible probabilistic sampling, and argue for an implementation based on finite-state factors. We propose a modular decomposition that reconciles generation accu
Publikováno v:
EACL
We propose a demonstration of a domainspecific terminology checking service which works on top of any generic blackbox MT, and only requires access to a bilingual terminology resource in the domain. In cases where an incorrect translation of a source