Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Wolfgang Macherey"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9, Pp 1460-1474 (2021)
AbstractHuman evaluation of modern high-quality machine translation systems is a difficult problem, and there is increasing evidence that inadequate evaluation procedures can lead to erroneous conclusions. While there has been considerable research o
Externí odkaz:
https://doaj.org/article/40f406ebbb294289a01d49fc645aacb2
Autor:
Ruiqing Zhang, Chuanqiang Zhang, Zhongjun He, Hua Wu, Haifeng Wang, Liang Huang, Qun Liu, Julia Ive, Wolfgang Macherey
Publikováno v:
Proceedings of the Third Workshop on Automatic Simultaneous Translation.
Publikováno v:
IWSLT
There has been great progress in improving streaming machine translation, a simultaneous paradigm where the system appends to a growing hypothesis as more source content becomes available. We study a related problem in which revisions to the hypothes
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::39d685370375aa9208e6dc5a19f43119
Publikováno v:
EMNLP (Findings)
We propose a simple and effective method for machine translation evaluation which does not require reference translations. Our approach is based on (1) grounding the entity mentions found in each source sentence and candidate translation against a la
Publikováno v:
ACL
In this paper, we propose a new adversarial augmentation method for Neural Machine Translation (NMT). The main idea is to minimize the vicinal risk over virtual sentences sampled from two vicinity distributions, of which the crucial one is a novel vi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3f6808394eda75bce00443b374b96129
Autor:
Chung-Cheng Chiu, Colin Raffel, Naveen Arivazhagan, Ruoming Pang, Colin Cherry, Wei Li, Semih Yavuz, Wolfgang Macherey
Publikováno v:
ACL (1)
Simultaneous machine translation begins to translate each source sentence before the source speaker is finished speaking, with applications to live and streaming scenarios. Simultaneous systems must carefully schedule their reading of the source sent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a327f333a7c39fddce90ade95b3c7e51
http://arxiv.org/abs/1906.05218
http://arxiv.org/abs/1906.05218
Publikováno v:
INTERSPEECH
We present an attention-based sequence-to-sequence neural network which can directly translate speech from one language into speech in another language, without relying on an intermediate text representation. The network is trained end-to-end, learni
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::15becfa04d691db2c4fd7fdf9e739506
Publikováno v:
ACL (1)
Neural machine translation (NMT) often suffers from the vulnerability to noisy perturbations in the input. We propose an approach to improving the robustness of NMT models, which consists of two parts: (1) attack the translation model with adversaria
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::966753bb483d94bef6a95bc963739baa
Publikováno v:
EMNLP
Translating characters instead of words or word-fragments has the potential to simplify the processing pipeline for neural machine translation (NMT), and improve results by eliminating hyper-parameters and manual feature engineering. However, it resu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::78ac007f62f9319df75799c2bd4a30b6
http://arxiv.org/abs/1808.09943
http://arxiv.org/abs/1808.09943
Autor:
Chung-Cheng Chiu, Yuan Cao, Ron Weiss, Wolfgang Macherey, Yonghui Wu, Stella Marie Laurenzo, Ye Jia, Naveen Ari, Melvin Johnson
Publikováno v:
ICASSP
End-to-end Speech Translation (ST) models have many potential advantages when compared to the cascade of Automatic Speech Recognition (ASR) and text Machine Translation (MT) models, including lowered inference latency and the avoidance of error compo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0d388dddc89b5f4044270d798cc12dc4