Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Yoav Artzi"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9, Pp 1303-1319 (2021)
AbstractWe study continual learning for natural language instruction generation, by observing human users’ instruction execution. We focus on a collaborative scenario, where the system both acts and delegates tasks to human users using natural lang
Externí odkaz:
https://doaj.org/article/df09a249402a44debc6aed2c01716cea
We study learning from user feedback for extractive question answering by simulating feedback using supervised data. We cast the problem as contextual bandit learning, and analyze the characteristics of several learning scenarios with focus on reduci
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4ea6b35aa97eb2e60480699bc7b4e421
Autor:
Felix Wu, Kwangyoun Kim, Shinji Watanabe, Kyu J. Han, Ryan McDonald, Kilian Q. Weinberger, Yoav Artzi
We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech recognition ta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::26b5e5a6b483bb52f21e1898429722c2
Autor:
G.L. Blankenship, Mari Ostendorf, Thomas M. Howard, Abeer Alwan, Debadeepta Dey, Carol Y. Espy-Wilson, Joyce Y. Chai, Ivana Kruijff-Korbayová, Cynthia Matuszek, David Traum, Roger K. Moore, Mary P. Harper, Nigel Ward, Robert St. Amant, Yoav Artzi, Tong Sun, Mohit Bansal, Heather Pon-Barry, Casey Kennington, Raymond J. Mooney, Hal Daumé, Dinesh Manocha, Stefanie Tellex, Ross Mead, Alexander I. Rudnicky, Matthew Marge, Matthias Scheutz, Zhou Yu
With robotics rapidly advancing, more effective human–robot interaction is increasingly needed to realize the full potential of robots for society. While spoken language must be part of the solution, our ability to provide spoken language interacti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::044c51d339513cbe60ef443ab0a567e9
https://eprints.whiterose.ac.uk/179240/7/1-s2.0-S0885230821000620-main.pdf
https://eprints.whiterose.ac.uk/179240/7/1-s2.0-S0885230821000620-main.pdf
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b8bbce43c48f3ed4a62510473cbb244f
https://doi.org/10.1109/iccv48922.2021.00141
https://doi.org/10.1109/iccv48922.2021.00141
Autor:
Alane Suhr, Clara Vania, Nikita Nangia, Maarten Sap, Mark Yatskar, Samuel R. Bowman, Yoav Artzi
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::902b87dda1960d315da12d2d1561444f
https://doi.org/10.18653/v1/2021.emnlp-tutorials.1
https://doi.org/10.18653/v1/2021.emnlp-tutorials.1
Publikováno v:
Proceedings of the Third International Workshop on Spatial Language Understanding.
The Touchdown dataset (Chen et al., 2019) provides instructions by human annotators for navigation through New York City streets and for resolving spatial descriptions at a given location. To enable the wider research community to work effectively wi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1b79d4c30f34f1322c1ef0a17b0d66c2
https://doi.org/10.18653/v1/2020.splu-1.7
https://doi.org/10.18653/v1/2020.splu-1.7
Publikováno v:
ACL
Visual features are a promising signal for learning bootstrap textual models. However, blackbox learning models make it difficult to isolate the specific contribution of visual components. In this analysis, we consider the case study of the Visually
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d19adb2566354f5ebba575f2a90e7f71
Publikováno v:
ACL
We study the potential for interaction in natural language classification. We add a limited form of interaction for intent classification, where users provide an initial query using natural language, and the system asks for additional information usi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9155db05b051a18290a1bc7d6c9cd07f
http://arxiv.org/abs/1911.03598
http://arxiv.org/abs/1911.03598
Publikováno v:
WWW
Rich engagement data can shed light on how people interact with online content and how such interactions may be determined by the content of the page. In this work, we investigate a specific type of interaction, backtracking, which refers to the acti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::408505c033101eb634c9b1723ae6c262
https://doi.org/10.1145/3308558.3313571
https://doi.org/10.1145/3308558.3313571