Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Yosi Mass"'
Autor:
Tamar Lavee, Daniel Hershcovich, Slava Shechtman, Yoav Katz, Guy Moshkowich, Shai Gretz, Yonatan Bilu, Ran Levy, Charles Jochim, Michal Jacovi, Lilach Edelstein, Assaf Toledo, Ariel Gera, Artem Spector, Eyal Shnarch, Aya Soffer, Benjamin Sznajder, Carlos Alzate, Ruty Rinott, Orith Toledo-Ronen, Noam Slonim, Dalia Krieger, Dan Gutfreund, Yosi Mass, Lili Kotlerman, Ranit Aharonov, Liat Ein-Dor, Dafna Sheinwald, Leshem Choshen, Dan Lahav, Amir Menczel, Ben Bogin, David Konopnicki, Yoav Kantor, Shay Hummel, Elad Venezian, Shachar Mirkin, Ilya Shnayderman, Ron Hoory, Roni Friedman-Melamed, Lena Dankin, Martin Gleize, Roy Bar-Haim, Francesca Bonin, Ella Rabinovich, Matan Orbach, Zvi Kons, Alon Halfon, Yufang Hou, Shila Ofek-Koifman, Naftali Liberman, Edo Cohen-Karlik, Assaf Gavron
Publikováno v:
Nature. 591:379-384
Artificial intelligence (AI) is defined as the ability of machines to perform tasks that are usually associated with intelligent beings. Argument and debate are fundamental capabilities of human intelligence, essential for a wide range of human activ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::01dd149822094d65fe7bf5ea23f9a8b7
https://doi.org/10.1038/s41586-021-03215-w
https://doi.org/10.1038/s41586-021-03215-w
We deal with the scenario of conversational search, where user queries are under-specified or ambiguous. This calls for a mixed-initiative setup. User-asks (queries) and system-answers, as well as system-asks (clarification questions) and user respon
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::27a6da27e157e883159c58d436884e04
http://arxiv.org/abs/2112.07308
http://arxiv.org/abs/2112.07308
Publikováno v:
ICTIR
The goal of the query performance prediction (QPP) task is to estimate retrieval effectiveness in the absence of relevance judgments. We consider a novel task of predicting the performance of multifield document retrieval. In this setting, documents
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f1b9fdad43953e5c2d91affbf9d5d186
https://doi.org/10.1145/3409256.3409821
https://doi.org/10.1145/3409256.3409821
Autor:
Haggai Roitman, Yosi Mass
Publikováno v:
EMNLP (1)
We describe a weakly-supervised method for training deep learning models for the task of ad-hoc document retrieval. Our method is based on generative and discriminative models that are trained using weak-supervision just from the documents in the cor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::914b9b695eaf386549effb5da8bc0f94
https://doi.org/10.18653/v1/2020.emnlp-main.343
https://doi.org/10.18653/v1/2020.emnlp-main.343
Autor:
Q. Vera Liao, R. Chulaka Gunasekara, Danish Contractor, Nathaniel Mills, Sachindra Joshi, Jatin Ganhotra, Doron Cohen, Yosi Mass, David Konopnicki, Shai Erera, Haggai Roitman, Siva Sankalp Patel, Luis A. Lastras, Kshitij P. Fadnis, Gaurav Pandey
Publikováno v:
EMNLP (Demos)
Customer support agents play a crucial role as an interface between an organization and its end-users. We propose CAIRAA: Conversational Approach to Information Retrieval for Agent Assistance, to reduce the cognitive workload of support agents who en
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::38dbc171ddf19eb728c0532306eb2cc6
https://doi.org/10.18653/v1/2020.emnlp-demos.20
https://doi.org/10.18653/v1/2020.emnlp-demos.20
Autor:
Luis A. Lastras, Yosi Mass, Jatin Ganhotra, R. Chulaka Gunasekara, Nathaniel Mills, Sachindra Joshi, David Konopnicki, Haggai Roitman, Doron Cohen
Publikováno v:
EMNLP (1)
A frequent pattern in customer care conversations is the agents responding with appropriate webpage URLs that address users' needs. We study the task of predicting the documents that customer care agents can use to facilitate users' needs. We also in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4afb8397a367e1d29835cd02d7242c0c
Publikováno v:
ACL
We focus on the task of Frequently Asked Questions (FAQ) retrieval. A given user query can be matched against the questions and/or the answers in the FAQ. We present a fully unsupervised method that exploits the FAQ pairs to train two BERT models. Th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::74cf1e1296bee03fe5431aa2e8ae44f8
https://doi.org/10.18653/v1/2020.acl-main.74
https://doi.org/10.18653/v1/2020.acl-main.74
Autor:
Yosi Mass, Haggai Roitman
Publikováno v:
ICTIR
The usage of passage-level information has been successfully demonstrated in many core IR tasks, and among such tasks, the task of passage-based document retrieval. In this work, we study the merits of utilizing similar information for the fusion-bas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d7cee9e7576134af3e048a1506b67837
https://doi.org/10.1145/3341981.3344212
https://doi.org/10.1145/3341981.3344212
Autor:
Shai Erera, Michal Shmueli-Scheuer, Guy Feigenblat, Ora Peled Nakash, Odellia Boni, Haggai Roitman, Doron Cohen, Bar Weiner, Yosi Mass, Or Rivlin, Guy Lev, Achiya Jerbi, Jonathan Herzig, Yufang Hou, Charles Jochim, Martin Gleize, Francesca Bonin, David Konopnicki
Publikováno v:
EMNLP/IJCNLP (3)
We present a novel system providing summaries for Computer Science publications. Through a qualitative user study, we identified the most valuable scenarios for discovery, exploration and understanding of scientific documents. Based on these findings
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9ac3475b8c24ba50f80760055d2152a6
https://doi.org/10.18653/v1/d19-3036
https://doi.org/10.18653/v1/d19-3036
Autor:
Ron Hoory, Slava Shechtman, Moran Mordechay, Oren Sar Shalom, Guy Lev, David Konopnicki, Yosi Mass
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1f0354d81fac07c070ad2cc46b3c0121
https://doi.org/10.21437/interspeech.2018-1159
https://doi.org/10.21437/interspeech.2018-1159