Zobrazeno 1 - 10
of 47
pro vyhledávání: '"Antonios Anastasopoulos"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9, Pp 1285-1302 (2021)
AbstractMuch of the existing linguistic data in many languages of the world is locked away in non- digitized books and documents. Optical character recognition (OCR) can be used to produce digitized text, and previous work has demonstrated the utilit
Externí odkaz:
https://doaj.org/article/36c3cbb49dc746b0a2b9638c326f28c0
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9, Pp 1-16 (2021)
AbstractActive learning (AL) uses a data selection algorithm to select useful training samples to minimize annotation cost. This is now an essential tool for building low-resource syntactic analyzers such as part-of-speech (POS) taggers. Existing AL
Externí odkaz:
https://doaj.org/article/98d044bf96054b06aa494cf3d95b90fa
Publikováno v:
2022 IEEE International Conference on Big Data (Big Data).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::53d18a1592a073e96c8e0c522facfc29
https://doi.org/10.1109/bigdata55660.2022.10020661
https://doi.org/10.1109/bigdata55660.2022.10020661
Recent work by S{\o}gaard (2020) showed that, treebank size aside, overlap between training and test graphs (termed leakage) explains more of the observed variation in dependency parsing performance than other explanations. In this work we revisit th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::234a502e6975df51e1b12c6ddf35b72e
Publikováno v:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5eb3a674dfe8eafa82ab28f846aaa856
https://doi.org/10.18653/v1/2022.acl-long.376
https://doi.org/10.18653/v1/2022.acl-long.376
Transliteration is very common on social media, but transliterated text is not adequately handled by modern neural models for various NLP tasks. In this work, we combine data augmentation approaches with a Teacher-Student training scheme to address t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fe34dfb585a409a8b9c7754602f73221
http://arxiv.org/abs/2108.13620
http://arxiv.org/abs/2108.13620
Autor:
Michael R. Marlo, David R. Mortensen, Kathleen Siminyu, Antonios Anastasopoulos, Graham Neubig, Xinjian Li
Models pre-trained on multiple languages have shown significant promise for improving speech recognition, particularly for low-resource languages. In this work, we focus on phoneme recognition using Allosaurus, a method for multilingual recognition b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::db7ee79b529b14de177bc1e3acc40a5a
http://arxiv.org/abs/2104.01624
http://arxiv.org/abs/2104.01624
Autor:
Jacob Bremerman, Satoshi Nakamura, Changhan Wang, Roldano Cattoni, Marco Turchi, Marcello Federico, Xutai Ma, Sebastian Stüker, Matthew Wiesner, Antonios Anastasopoulos, Maha Elbayad, Katsuhito Sudoh, Matteo Negri, Ondrej Bojar, Juan Pino, Elizabeth Salesky, Jan Niehues, Alex Waibel
Publikováno v:
IWSLT 2021: THE 18TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE TRANSLATION, 1-29
STARTPAGE=1;ENDPAGE=29;TITLE=IWSLT 2021: THE 18TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE TRANSLATION
Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)
IWSLT
STARTPAGE=1;ENDPAGE=29;TITLE=IWSLT 2021: THE 18TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE TRANSLATION
Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)
IWSLT
The evaluation campaign of the International Conference on Spoken Language Translation (IWSLT 2021) featured this year four shared tasks: (i) Simultaneous speech translation, (ii) Offline speech translation, (iii) Multilingual speech translation, (iv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f99a86a3779444c0ff0a3703891ec7bd
https://cris.maastrichtuniversity.nl/en/publications/b700c4f5-c944-426b-9b60-10991fcbbc81
https://cris.maastrichtuniversity.nl/en/publications/b700c4f5-c944-426b-9b60-10991fcbbc81
Automated source code summarization is a popular software engineering research topic wherein machine translation models are employed to "translate" code snippets into relevant natural language descriptions. Most evaluations of such models are conduct
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::673cb4def117ed53ee5a887d0cd5e6a0
As language technologies become more ubiquitous, there are increasing efforts towards expanding the language diversity and coverage of natural language processing (NLP) systems. Arguably, the most important factor influencing the quality of modern NL
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4ebd63eae69a46023b3ea77ccee0477f