Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Denis Peskov"'
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eef92d3fd7e029b18216ff47d2b6ca1c
https://doi.org/10.18653/v1/2021.findings-emnlp.315
https://doi.org/10.18653/v1/2021.findings-emnlp.315
Publikováno v:
COLING
Recent high scores on pronoun translation using context-aware neural machine translation have suggested that current approaches work well. ContraPro is a notable example of a contrastive challenge set for English→German pronoun translation. The hig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dd53c00c3d9205a2105ac15b26579f83
https://doi.org/10.18653/v1/2020.coling-main.417
https://doi.org/10.18653/v1/2020.coling-main.417
Autor:
Joe Barrow, Cristian Danescu-Niculescu-Mizil, Benny Cheng, Jordan Boyd-Graber, Ahmed Elgohary, Denis Peskov
Publikováno v:
ACL
Trust is implicit in many online text conversations—striking up new friendships, or asking for tech support. But trust can be betrayed through deception. We study the language and dynamics of deception in the negotiation-based game Diplomacy, where
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::83908fbc8a68351e548bdab822cf406e
https://doi.org/10.18653/v1/2020.acl-main.353
https://doi.org/10.18653/v1/2020.acl-main.353
Publikováno v:
INTERSPEECH
Natural language processing systems are often downstream of unreliable inputs: machine translation, optical character recognition, or speech recognition. For instance, virtual assistants can only answer your questions after understanding your speech.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::39951000438dd8c0cd30154516247ae0
https://doi.org/10.21437/interspeech.2019-3154
https://doi.org/10.21437/interspeech.2019-3154
Autor:
Lisa Maszkiewicz, Kristina Gligoric, Sean Kross, Emily Hwang, Denis Peskov, Dhruv Kuchhal, Rock Stevens, Sudha Rao, Hal Daumé, Michelle L. Mazurek, Elissa M. Redmiles, Miraida Morales, Everest Liu
Publikováno v:
EMNLP/IJCNLP (1)
The readability of a digital text can influence people’s ability to learn new things about a range topics from digital resources (e.g., Wikipedia, WebMD). Readability also impacts search rankings, and is used to evaluate the performance of NLP syst
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::96ba470bd8a75d6e2aa245dac4b805b4
https://doi.org/10.18653/v1/d19-1489
https://doi.org/10.18653/v1/d19-1489
Publikováno v:
EMNLP/IJCNLP (1)
The need for high-quality, large-scale, goal-oriented dialogue datasets continues to grow as virtual assistants become increasingly wide-spread. However, publicly available datasets useful for this area are limited either in their size, linguistic di
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::023d136460813fa8a4515244f3e60b1d
https://doi.org/10.18653/v1/d19-1460
https://doi.org/10.18653/v1/d19-1460
Autor:
Joe Barrow, Denis Peskov
Publikováno v:
SemEval@ACL
We describe a modified shared-LSTM network for the Semantic Textual Similarity (STS) task at SemEval-2017. The network builds on previously explored Siamese network architectures. We treat max sentence length as an additional hyperparameter to be tun
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7f931c27f77babefb84bda2505a270d4
https://doi.org/10.18653/v1/s17-2026
https://doi.org/10.18653/v1/s17-2026