Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Roee Aharoni"'
Neural knowledge-grounded generative models for dialogue often produce content that is factually inconsistent with the knowledge they rely on, making them unreliable and limiting their applicability. Inspired by recent work on evaluating factual cons
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ac3b4e9c7c19bc32c02c0f57d4ec93cd
http://arxiv.org/abs/2104.08202
http://arxiv.org/abs/2104.08202
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030660956
ECCV Workshops (2)
ECCV Workshops (2)
We propose a lightweight real-time sign language detection model, as we identify the need for such a case in videoconferencing. We extract optical flow features based on human pose estimation and, using a linear classifier, show these features are me
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::14021a38555db07f0da4493a15f93f74
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
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0d2a035e4b998ef95f842b3324dbe5db
https://doi.org/10.18653/v1/2020.findings-emnlp.287
https://doi.org/10.18653/v1/2020.findings-emnlp.287
Autor:
Yoav Goldberg, Roee Aharoni
Publikováno v:
ACL
The notion of "in-domain data" in NLP is often over-simplistic and vague, as textual data varies in many nuanced linguistic aspects such as topic, style or level of formality. In addition, domain labels are many times unavailable, making it challengi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b777489cb4401edc527f40fd649e3a8d
Publikováno v:
CoNLL
Phenomenon-specific "adversarial" datasets have been recently designed to perform targeted stress-tests for particular inference types. Recent work (Liu et al., 2019a) proposed that such datasets can be utilized for training NLI and other types of mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3ab6e614bc2e3349433175f7121c02a1
http://arxiv.org/abs/1910.09302
http://arxiv.org/abs/1910.09302
When translating from a language that does not morphologically mark information such as gender and number into a language that does, translation systems must "guess" this missing information, often leading to incorrect translations in the given conte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::43abad80bcab67b68f033e1b5e5b7837
Publikováno v:
NAACL-HLT (1)
Multilingual neural machine translation (NMT) enables training a single model that supports translation from multiple source languages into multiple target languages. In this paper, we push the limits of multilingual NMT in terms of number of languag
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4424f3c54cead041d402c17538dc0faa
Autor:
Yoav Goldberg, Roee Aharoni
Publikováno v:
ACL (2)
Splitting and rephrasing a complex sentence into several shorter sentences that convey the same meaning is a challenging problem in NLP. We show that while vanilla seq2seq models can reach high scores on the proposed benchmark (Narayan et al., 2017),
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::909130860958d73f3cc923b26b1881b9
https://doi.org/10.18653/v1/p18-2114
https://doi.org/10.18653/v1/p18-2114
Autor:
Yoav Goldberg, Roee Aharoni
Publikováno v:
ACL (2)
We present a simple method to incorporate syntactic information about the target language in a neural machine translation system by translating into linearized, lexicalized constituency trees. An experiment on the WMT16 German-English news translatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::61eb1f060f0a28a1291921f64f7f0be4
Autor:
Roee Aharoni, Yoav Goldberg
Publikováno v:
ACL (1)
We present a neural model for morphological inflection generation which employs a hard attention mechanism, inspired by the nearly-monotonic alignment commonly found between the characters in a word and the characters in its inflection. We evaluate t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::14af3073c2e857e917159f75103115ca
https://doi.org/10.18653/v1/p17-1183
https://doi.org/10.18653/v1/p17-1183