Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Hisami Suzuki"'
Autor:
Tasos Anastasakos, Paul A. Crook, Hisami Suzuki, Zhaleh Feizollahi, Ruhi Sarikaya, Roman Holenstein, E. Krawczyk, Jean-Philippe Robichaud, Vasiliy Radostev, Daniel Boies, Nikhil Ramesh, Young-Bum Kim, Alexandre Rochette, Alex Marin, Omar Zia Khan, Minwoo Jeong, Xiaohu Liu, Asli Celikyilmaz
Publikováno v:
SLT
Spoken language understanding and dialog management have emerged as key technologies in interacting with personal digital assistants (PDAs). The coverage, complexity, and the scale of PDAs are much larger than previous conversational understanding sy
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::29ffcdb8af965d83dae4807bc6b9ca3e
https://doi.org/10.1109/slt.2016.7846294
https://doi.org/10.1109/slt.2016.7846294
Publikováno v:
Information Processing & Management
In recent years, there has been increased interest in topic-focused multi-document summarization. In this task, automatic summaries are produced in response to a specific information request, or topic, stated by the user. The system we have designed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c41aeff1eeba770227658eb936f3ef73
https://doi.org/10.1016/j.ipm.2007.01.023
https://doi.org/10.1016/j.ipm.2007.01.023
Publikováno v:
ACM Transactions on Asian Language Information Processing. 5:209-227
This article presents an empirical study of four techniques for adapting language models, including a maximum a posteriori (MAP) method and three discriminative training models, in the application of Japanese Kana-Kanji conversion. We compare the per
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bcb9153064d21e181e28f519c1cdc5b7
https://doi.org/10.1145/1194936.1194939
https://doi.org/10.1145/1194936.1194939
Autor:
Jun Hatori, Hisami Suzuki
Publikováno v:
Computational Linguistics and Intelligent Text Processing ISBN: 9783642194368
CICLing (2)
CICLing (2)
This paper addresses the problem of predicting the pronunciation of Japanese words, especially those that are newly created and therefore not in the dictionary. This is an important task for many applications including text-to-speech and text input m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::01934581dfc0c11be40e0fbb985b949d
https://doi.org/10.1007/978-3-642-19437-5_40
https://doi.org/10.1007/978-3-642-19437-5_40
Autor:
Colin Cherry, Hisami Suzuki
Publikováno v:
EMNLP
We present a discriminative substring decoder for transliteration. This decoder extends recent approaches for discriminative character transduction by allowing for a list of known target-language words, an important resource for transliteration. Our
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::377ff3134d1c764f0ede6163b76f54cc
https://doi.org/10.3115/1699648.1699652
https://doi.org/10.3115/1699648.1699652
Autor:
Hisami Suzuki, Masato Hagiwara
Publikováno v:
Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics on - NAACL '09.
We propose a unified approach to web search query alterations in Japanese that is not limited to particular character types or orthographic similarity between a query and its alteration candidate. Our model is based on previous work on English query
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6726eba97aea7172517741d7d9778bd0
https://doi.org/10.3115/1620754.1620782
https://doi.org/10.3115/1620754.1620782
Autor:
Hisami Suzuki, Colin Cherry
Publikováno v:
NEWS@IJCNLP
We interpret the problem of transliterating English named entities into Hindi or Japanese Katakana as a variant of the letter-to-phoneme (L2P) subtask of text-to-speech processing. Therefore, we apply a re-implementation of a state-of-the-art, discri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e6da353d06b9ee5b695cb506ce4e3446
https://doi.org/10.3115/1699705.1699723
https://doi.org/10.3115/1699705.1699723
Publikováno v:
EMNLP
In this paper we address the problem of identifying a broad range of term variations in Japanese web search queries, where these variations pose a particularly thorny problem due to the multiple character types employed in its writing system. Our met
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e74ecfed4c8868ba065c731a62da0df1
https://doi.org/10.3115/1699648.1699695
https://doi.org/10.3115/1699648.1699695
Autor:
Satoshi Sekine, Hisami Suzuki
Publikováno v:
WWW
We present a method for acquiring ontological knowledge using search query logs. We first use query logs to identify important contexts associated with terms belonging to a semantic category; we then use these contexts to harvest new words belonging
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::97a375e415b130e25e383b63df650836
https://doi.org/10.1145/1242572.1242777
https://doi.org/10.1145/1242572.1242777
Publikováno v:
ACL
Lasso is a regularization method for parameter estimation in linear models. It optimizes the model parameters with respect to a loss function subject to model complexities. This paper explores the use of lasso for statistical language modeling for te
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::06adbde6560aefccda6abb107b06ddf7
https://doi.org/10.3115/1220175.1220204
https://doi.org/10.3115/1220175.1220204