Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Patrick Simianer"'
Publikováno v:
Machine Translation. 32:309-324
The advantages of neural machine translation (NMT) have been extensively validated for offline translation of several language pairs for different domains of spoken and written language. However, research on interactive learning of NMT by adaptation
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b3ec9efe8dbdd479af87c7bfcbea7c5f
https://doi.org/10.1007/s10590-018-9224-8
https://doi.org/10.1007/s10590-018-9224-8
Publikováno v:
NAACL-HLT (1)
Incremental domain adaptation, in which a system learns from the correct output for each input immediately after making its prediction for that input, can dramatically improve system performance for interactive machine translation. Users of interacti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::51c4b31be646e8fd68b03292613c074a
https://doi.org/10.18653/v1/n19-1206
https://doi.org/10.18653/v1/n19-1206
Publikováno v:
EMNLP
We propose and compare methods for gradient-based domain adaptation of self-attentive neural machine translation models. We demonstrate that a large proportion of model parameters can be frozen during adaptation with minimal or no reduction in transl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::696ab6e958b666873310c3d4bf43babd
http://arxiv.org/abs/1811.01990
http://arxiv.org/abs/1811.01990
Autor:
Patrick Simianer, Mauro Cettolo, Katharina Wäschle, Stefan Riezler, Nicola Bertoldi, Marcello Federico
Publikováno v:
Machine Translation. 28:309-339
Recent research has shown that accuracy and speed of human translators can benefit from post-editing output of machine translation systems, with larger benefits for higher quality output. We present an efficient online learning framework for adapting
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::df1d47746761d324b20165ba4f854e7e
https://doi.org/10.1007/s10590-014-9159-7
https://doi.org/10.1007/s10590-014-9159-7
Publikováno v:
The Prague Bulletin of Mathematical Linguistics. 96:99-108
Multi-Task Minimum Error Rate Training for SMT We present experiments on multi-task learning for discriminative training in statistical machine translation (SMT), extending standard minimum-error-rate training (MERT) by techniques that take advantage
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e443d47c2eab8ba7952837ae3e986fbb
https://doi.org/10.2478/v10108-011-0015-0
https://doi.org/10.2478/v10108-011-0015-0
Publikováno v:
ACL (1)
We propose a novel learning approach for statistical machine translation (SMT) that allows to extract supervision signals for structured learning from an extrinsic response to a translation input. We show how to generate responses by grounding SMT in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4306d180d265da92ccdbeee0bc762968
https://doi.org/10.3115/v1/p14-1083
https://doi.org/10.3115/v1/p14-1083