Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Tom Kenter"'
Autor:
Lev Finkelstein, Heiga Zen, Norman Casagrande, Chun-an Chan, Ye Jia, Tom Kenter, Alex Petelin, Jonathan Shen, Vincent Wan, Yu Zhang, Yonghui Wu, Robert Clark
Transfer tasks in text-to-speech (TTS) synthesis - where one or more aspects of the speech of one set of speakers is transferred to another set of speakers that do not feature these aspects originally - remains a challenging task. One of the challeng
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9b4ec8728b0902a310793207cc888c8a
http://arxiv.org/abs/2208.13183
http://arxiv.org/abs/2208.13183
Publikováno v:
IEEE Transactions on Knowledge and Data Engineering, 31(11), 2124-2137. IEEE Computer Society
A high degree of topical diversity is often considered to be an important characteristic of interesting text documents. A recent proposal for measuring topical diversity identifies three distributions for assessing the diversity of documents: distrib
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fbf904a8c21bb10f013602e2992cc94c
https://dare.uva.nl/personal/pure/en/publications/hitr-hierarchical-topic-model-reestimation-for-measuring-topical-diversity-of-documents(3cc89ac9-eed7-49f0-9815-582d9a4bf652).html
https://dare.uva.nl/personal/pure/en/publications/hitr-hierarchical-topic-model-reestimation-for-measuring-topical-diversity-of-documents(3cc89ac9-eed7-49f0-9815-582d9a4bf652).html
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cda34f915cefe046032860a771816e3e
https://doi.org/10.21437/interspeech.2020-1437
https://doi.org/10.21437/interspeech.2020-1437
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b51621bfc5d6af414a01d108da5fe5f0
https://doi.org/10.21437/interspeech.2020-1430
https://doi.org/10.21437/interspeech.2020-1430
Publikováno v:
ACL
Lexica distinguishing all morphologically related forms of each lexeme are crucial to many language technologies, yet building them is expensive. We propose a frugal paradigm completion approach that predicts all related forms in a morphological para
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3ebe6a090f4d0b16015c1c2908d33c9e
https://doi.org/10.18653/v1/2020.acl-main.733
https://doi.org/10.18653/v1/2020.acl-main.733
Autor:
Tom Kenter, Krisztian Balog
Publikováno v:
ICTIR
Knowledge graphs, organizing structured information about entities, and their attributes and relationships, are ubiquitous today. Entities, in this context, are usually taken to be anyone or anything considered to be globally important. This, however
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ff48cf753f2dd6a570d3487acb72bc4e
https://doi.org/10.1145/3341981.3344241
https://doi.org/10.1145/3341981.3344241
Text-to-speech systems are typically evaluated on single sentences. When long-form content, such as data consisting of full paragraphs or dialogues is considered, evaluating sentences in isolation is not always appropriate as the context in which the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::01f9602d1de6795ad048d93032fa6faa
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 32
The machine reading task, where a computer reads a document and answers questions about it, is important in artificial intelligence research. Recently, many models have been proposed to address it. Word-level models, which have words as units of inpu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::70d9534d9e289b4631236309d6b345a0
https://doi.org/10.1609/aaai.v32i1.12050
https://doi.org/10.1609/aaai.v32i1.12050
Publikováno v:
Information Processing & Management, 51(6), 791-808. Elsevier
We propose a new way of measuring document filtering system performance over time.Performance is calculated per batch and a trend line is fitted to the results.Systems are compared by their performance at the end of the evaluation period.Important in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::55d7f49b1c9e5c7adb69337bc274e6ae
https://doi.org/10.1016/j.ipm.2015.03.005
https://doi.org/10.1016/j.ipm.2015.03.005
Autor:
Maarten de Rijke, Tom Kenter, Arjen P. de Vries, ChengXiang Zhai, Franciska de Jong, Kira Radinsky, Katja Hofmann
This book constitutes the proceedings of the 36th European Conference on IR Research, ECIR 2014, held in Amsterdam, The Netherlands, in April 2014.The 33 full papers, 50 poster papers and 15 demonstrations presented in this volume were carefully revi