Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Shamil Chollampatt"'
Publikováno v:
EMNLP (1)
Automatic post-editing (APE) aims to improve machine translations, thereby reducing human post-editing effort. APE has had notable success when used with statistical machine translation (SMT) systems but has not been as successful over neural machine
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0464d1cc88b4f965ddb5994c25b75044
https://doi.org/10.18653/v1/2020.emnlp-main.217
https://doi.org/10.18653/v1/2020.emnlp-main.217
Publikováno v:
ACL
This paper proposes a simple and effective algorithm for incorporating lexical constraints in neural machine translation. Previous work either required re-training existing models with the lexical constraints or incorporating them during beam search
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::74ca522811d55507c229f84087e1f737
https://doi.org/10.18653/v1/2020.acl-main.325
https://doi.org/10.18653/v1/2020.acl-main.325
Publikováno v:
ACL (1)
Automatic grammatical error correction (GEC) research has made remarkable progress in the past decade. However, all existing approaches to GEC correct errors by considering a single sentence alone and ignoring crucial cross-sentence context. Some err
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fcc4dc529077b618e6004c093ef2916c
https://doi.org/10.18653/v1/p19-1042
https://doi.org/10.18653/v1/p19-1042
Autor:
Shamil Chollampatt, Hwee Tou Ng
We improve automatic correction of grammatical, orthographic, and collocation errors in text using a multilayer convolutional encoder-decoder neural network. The network is initialized with embeddings that make use of character N-gram information to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8940fc70d91b49665d7bdfc634810abb
http://arxiv.org/abs/1801.08831
http://arxiv.org/abs/1801.08831
Autor:
Hwee Tou Ng, Shamil Chollampatt
Publikováno v:
EMNLP
Grammatical error correction (GEC) systems deployed in language learning environments are expected to accurately correct errors in learners’ writing. However, in practice, they often produce spurious corrections and fail to correct many errors, the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fd75c802e087ee69d54f6067c8d8881b
https://doi.org/10.18653/v1/d18-1274
https://doi.org/10.18653/v1/d18-1274
Publikováno v:
EMNLP
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8ed05024872b445ba885877bb06bab79
https://doi.org/10.18653/v1/d16-1195
https://doi.org/10.18653/v1/d16-1195