Zobrazeno 1 - 10
of 149
pro vyhledávání: '"Monica S. Lam"'
Publikováno v:
The Adjunct Publication of the 35th Annual ACM Symposium on User Interface Software and Technology.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c8f6fcc6d24db54bf8594e5ce2a329d2
https://doi.org/10.1145/3526114.3558709
https://doi.org/10.1145/3526114.3558709
Publikováno v:
CHI Conference on Human Factors in Computing Systems.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::61add3b6f42d2b1d020d36c7fa880668
https://doi.org/10.1145/3491102.3502045
https://doi.org/10.1145/3491102.3502045
Publikováno v:
PLDI
While Alexa can perform over 100,000 skills, its capability covers only a fraction of what is possible on the web. Individuals need and want to automate a long tail of web-based tasks which often involve visiting different websites and require progra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b8549d675ef3410f3dfd4ceb8e37fa29
https://doi.org/10.1145/3453483.3454046
https://doi.org/10.1145/3453483.3454046
Publikováno v:
XRDS: Crossroads, The ACM Magazine for Students. 26:40-44
Will Alexa and Google Assistant become the duopoly platforms on which consumers reach web services and IoTs verbally? With open and collaborative research, we can build the best open-source virtual assistant to ensure choice, privacy, and open compet
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7f8aa256e2afa76c8e5984b7d28b7be0
https://doi.org/10.1145/3355757
https://doi.org/10.1145/3355757
Autor:
Sam Masling, Larry Heck, Nancy Xu, James A. Landay, Monica S. Lam, Giovanni Campagna, Michael Du
Publikováno v:
NAACL-HLT
Grounding natural language instructions on the web to perform previously unseen tasks enables accessibility and automation. We introduce a task and dataset to train AI agents from open-domain, step-by-step instructions originally written for people.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9fcbc912aa5273941c43595c3e14e322
https://doi.org/10.18653/v1/2021.naacl-main.80
https://doi.org/10.18653/v1/2021.naacl-main.80
Publikováno v:
UIST
Many computing tasks, such as comparison shopping, two-factor authentication, and checking movie reviews, require using multiple apps together. On large screens, "windows, icons, menus, pointer" (WIMP) graphical user interfaces (GUIs) support easy sh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8be1f5dec38abd6f096c9c4526304b3d
https://doi.org/10.1145/3379337.3415841
https://doi.org/10.1145/3379337.3415841
Autor:
Yi-Shan Lin, Chun-Ting Liu, Giovanni Campagna, Shih-Wei Liao, Monica S. Lam, De-Yi Tsai, Wei-Kang Fu, Chung-Huan Mei, Edward Y. Chang
Publikováno v:
2020 IEEE Infrastructure Conference.
Soteria is a user right management system designed to safeguard user-data privacy in a transparent and provable manner in compliance to regulations such as GDPR and CCPA. Soteria represents user data rights as formal executable sharing agreements, wh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ca2a6e294cf30f264396d320faf454c1
https://doi.org/10.1109/ieeeconf47748.2020.9377624
https://doi.org/10.1109/ieeeconf47748.2020.9377624
Publikováno v:
ACL
Zero-shot transfer learning for multi-domain dialogue state tracking can allow us to handle new domains without incurring the high cost of data acquisition. This paper proposes new zero-short transfer learning technique for dialogue state tracking wh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d843c85354a184ed161b687a7bc0585d
http://arxiv.org/abs/2005.00891
http://arxiv.org/abs/2005.00891
Publikováno v:
CHI
Although state-of-the-art smart speakers can hear a user's speech, unlike a human assistant these devices cannot figure out users' verbal references based on their head location and orientation. Soundr presents a novel interaction technique that leve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1b26e3d739bdc317f0fab060635301ed
https://doi.org/10.1145/3313831.3376427
https://doi.org/10.1145/3313831.3376427
Publikováno v:
EMNLP (1)
We propose Semantic Parser Localizer (SPL), a toolkit that leverages Neural Machine Translation (NMT) systems to localize a semantic parser for a new language. Our methodology is to (1) generate training data automatically in the target language by a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6cc8fdec0accc1575ed2eccea0605a16
https://doi.org/10.18653/v1/2020.emnlp-main.481
https://doi.org/10.18653/v1/2020.emnlp-main.481