Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Sperber, Matthias"'
Autor:
Sperber, Matthias, Bojar, Ondřej, Haddow, Barry, Javorský, Dávid, Ma, Xutai, Negri, Matteo, Niehues, Jan, Polák, Peter, Salesky, Elizabeth, Sudoh, Katsuhito, Turchi, Marco
Publikováno v:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Human evaluation is a critical component in machine translation system development and has received much attention in text translation research. However, little prior work exists on the topic of human evaluation for speech translation, which adds add
Externí odkaz:
http://arxiv.org/abs/2406.03881
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 7, Pp 313-325 (2019)
Speech translation has traditionally been approached through cascaded models consisting of a speech recognizer trained on a corpus of transcribed speech, and a machine translation system trained on parallel texts. Several recent works have shown the
Externí odkaz:
https://doaj.org/article/ec0209656f3c4c0cb272740ed21cee1d
Autor:
Alastruey, Belen, Sperber, Matthias, Gollan, Christian, Telaar, Dominic, Ng, Tim, Agarwal, Aashish
Code-switching (CS), i.e. mixing different languages in a single sentence, is a common phenomenon in communication and can be challenging in many Natural Language Processing (NLP) settings. Previous studies on CS speech have shown promising results f
Externí odkaz:
http://arxiv.org/abs/2310.12648
Behavioral testing in NLP allows fine-grained evaluation of systems by examining their linguistic capabilities through the analysis of input-output behavior. Unfortunately, existing work on behavioral testing in Machine Translation (MT) is currently
Externí odkaz:
http://arxiv.org/abs/2309.02553
Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool. In this wor
Externí odkaz:
http://arxiv.org/abs/2212.09982
Autor:
Weller, Orion, Sperber, Matthias, Pires, Telmo, Setiawan, Hendra, Gollan, Christian, Telaar, Dominic, Paulik, Matthias
Code switching (CS) refers to the phenomenon of interchangeably using words and phrases from different languages. CS can pose significant accuracy challenges to NLP, due to the often monolingual nature of the underlying systems. In this work, we focu
Externí odkaz:
http://arxiv.org/abs/2204.05076
Using end-to-end models for speech translation (ST) has increasingly been the focus of the ST community. These models condense the previously cascaded systems by directly converting sound waves into translated text. However, cascaded models have the
Externí odkaz:
http://arxiv.org/abs/2101.09149
Autor:
Sperber, Matthias, Setiawan, Hendra, Gollan, Christian, Nallasamy, Udhyakumar, Paulik, Matthias
The conventional paradigm in speech translation starts with a speech recognition step to generate transcripts, followed by a translation step with the automatic transcripts as input. To address various shortcomings of this paradigm, recent work explo
Externí odkaz:
http://arxiv.org/abs/2007.12741
Variational Neural Machine Translation (VNMT) is an attractive framework for modeling the generation of target translations, conditioned not only on the source sentence but also on some latent random variables. The latent variable modeling may introd
Externí odkaz:
http://arxiv.org/abs/2005.13978
Autor:
Sperber, Matthias, Paulik, Matthias
Over its three decade history, speech translation has experienced several shifts in its primary research themes; moving from loosely coupled cascades of speech recognition and machine translation, to exploring questions of tight coupling, and finally
Externí odkaz:
http://arxiv.org/abs/2004.06358