Zobrazeno 1 - 10
of 258
pro vyhledávání: '"Andrei Popescu Belis"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 6 (2021)
Externí odkaz:
https://doaj.org/article/290226bc25d84219a6bc857d2cb4e979
Publikováno v:
Linguistica Antverpiensia, New Series – Themes in Translation Studies. 8
A large number of evaluation metrics exist for machine translation (MT) systems, but depending on the intended context of use of such a system, not all metrics are equally relevant. Based on the ISO/IEC 9126 and 14598 standards for software evaluatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9c2c2d63604f774fa77f88d873d882b6
https://doi.org/10.52034/lanstts.v8i.244
https://doi.org/10.52034/lanstts.v8i.244
Autor:
Nikolaos Pappas, Andrei Popescu-Belis
Publikováno v:
Expert Systems with Applications. 43:23-41
A sentiment-aware one-class collaborative filtering method is proposed.The method integrates user sentiment with ratings via fixed or learned mappings.The method compares favorably with other models on three large multimedia datasets.Improvements are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1a234ff933ae903ed73b38d864d56ec8
https://doi.org/10.1016/j.eswa.2015.08.035
https://doi.org/10.1016/j.eswa.2015.08.035
Publikováno v:
Transactions of the Association for Computational Linguistics
This paper demonstrates that word sense disambiguation (WSD) can improve neural machine translation (NMT) by widening the source context considered when modeling the senses of potentially ambiguous words. We first introduce three adaptive clustering
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c5d5ab4af879aab898eebada6fc0419f
https://doi.org/10.5281/zenodo.2275709
https://doi.org/10.5281/zenodo.2275709
Publikováno v:
NAACL-HLT
arXiv.org e-Print Archive
Scopus-Elsevier
arXiv.org e-Print Archive
Scopus-Elsevier
Neural sequence-to-sequence networks with attention have achieved remarkable performance for machine translation. One of the reasons for their effectiveness is their ability to capture relevant source-side contextual information at each time-step pre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b666210507f60044dd3b10984e58d672
Autor:
Maryam Habibi, Andrei Popescu-Belis
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 23:746-759
This paper addresses the problem of keyword extraction from conversations, with the goal of using these keywords to retrieve, for each short conversation fragment, a small number of potentially relevant documents, which can be recommended to particip
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5f62d412a127b2018f23200c9ad4c155
https://doi.org/10.1109/taslp.2015.2405482
https://doi.org/10.1109/taslp.2015.2405482
Publikováno v:
IEEE Transactions on Audio Speech and Language Processing
This paper shows that the automatic labeling of discourse connectives with the relations they signal, prior to machine translation (MT), can be used by phrase-based statistical MT systems to improve their translations. This improvement is demonstrate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d7a706e4182aa3a98167b59f0bbf5f45
Publikováno v:
Infoscience-École polytechnique fédérale de Lausanne
EACL (1)
EACL (1)
We propose a method to decide whether two occurrences of the same noun in a source text should be translated consistently, i.e. using the same noun in the target text as well. We train and test classifiers that predict consistent translations based o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7043b8ee37b228a5606a573f1c641305
http://infoscience.epfl.ch/record/226627
http://infoscience.epfl.ch/record/226627
Publikováno v:
Formal Models in the Study of Language ISBN: 9783319488318
Discourse connectives are procedural markers of textual cohesion that have long been an object of study in the Geneva school of pragmatics. In this chapter, we argue that Jacques Moeschler’s descriptions of causal connectives have contributed to pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bd6a8ffdb2ec88fcf3dde51b0f80dde6
https://doi.org/10.1007/978-3-319-48832-5_20
https://doi.org/10.1007/978-3-319-48832-5_20
Publikováno v:
WMT
Proceedings of Second Conference on Machine Translation (WMT17)
Scopus-Elsevier
Proceedings of Second Conference on Machine Translation (WMT17)
Scopus-Elsevier
Statistical machine translation (SMT) systems use local cues from n-gram translation and language models to select the translation of each source word. Such systems do not explicitly perform word sense disambiguation (WSD), although this would enable
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5d81ce02fbae23925013c1848c735842
https://doi.org/10.18653/v1/w17-4701
https://doi.org/10.18653/v1/w17-4701