Zobrazeno 1 - 10
of 54
pro vyhledávání: '"Christof Monz"'
Publikováno v:
ACM Transactions on Information Systems, 39(4):47. Association for Computing Machinery (ACM)
In this paper, we address the problem of answering complex information needs by conversing conversations with search engines, in the sense that users can express their queries in natural language, and directly receivethe information they need from a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d3e555bcce41b161c6cf497c97c3eeb5
https://doi.org/10.1145/3432726
https://doi.org/10.1145/3432726
Publikováno v:
AAAI
AAAI-20, IAAI-20, EAAI-20 proceedings: Thirty-Fourth AAAI Conference on Artificial Intelligence, Thirty-Second Conference on Innovative Applications of Artificial Intelligence, The Tenth Symposium on Educational Advances in Artificial Intelligence : February 7–12th, 2020, New York Hilton Midtown, New York, New York, USA, 5, 8697-8704
AAAI-20, IAAI-20, EAAI-20 proceedings: Thirty-Fourth AAAI Conference on Artificial Intelligence, Thirty-Second Conference on Innovative Applications of Artificial Intelligence, The Tenth Symposium on Educational Advances in Artificial Intelligence : February 7–12th, 2020, New York Hilton Midtown, New York, New York, USA, 5, 8697-8704
Background Based Conversations (BBCs) have been introduced to help conversational systems avoid generating overly generic responses. In a BBC, the conversation is grounded in a knowledge source. A key challenge in BBCs is Knowledge Selection (KS): gi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::68ebee8e740ac3f339a79c9070b70376
https://dare.uva.nl/personal/pure/en/publications/thinking-globally-acting-locally-distantly-supervised-globaltolocal-knowledge-selection-for-background-based-conversation(ff3b1ca3-4678-4751-807e-5e2ecbb5cc7b).html
https://dare.uva.nl/personal/pure/en/publications/thinking-globally-acting-locally-distantly-supervised-globaltolocal-knowledge-selection-for-background-based-conversation(ff3b1ca3-4678-4751-807e-5e2ecbb5cc7b).html
Autor:
Christof Monz, Marzieh Fadaee
Publikováno v:
NGT@ACL
Recent works have shown that Neural Machine Translation (NMT) models achieve impressive performance, however, questions about understanding the behavior of these models remain unanswered. We investigate the unexpected volatility of NMT models where t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5b256da3bd2fddb14bbfa5d8e71028d0
https://doi.org/10.18653/v1/2020.ngt-1.10
https://doi.org/10.18653/v1/2020.ngt-1.10
Autor:
Christof Monz, Praveen Dakwale
Publikováno v:
Prague Bulletin of Mathematical Linguistics, Vol 108, Iss 1, Pp 37-48 (2017)
Neural machine translation is a recently proposed approach which has shown competitive results to traditional MT approaches. Standard neural MT is an end-to-end neural network where the source sentence is encoded by a recurrent neural network (RNN) c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4241783545f71e025801692423f48d7a
https://doaj.org/article/2115762c94e64b4caa3053402f8b505b
https://doaj.org/article/2115762c94e64b4caa3053402f8b505b
Publikováno v:
AAAI-20, IAAI-20, EAAI-20 proceedings: Thirty-Fourth AAAI Conference on Artificial Intelligence, Thirty-Second Conference on Innovative Applications of Artificial Intelligence, The Tenth Symposium on Educational Advances in Artificial Intelligence : February 7–12th, 2020, New York Hilton Midtown, New York, New York, USA, 5, 8496-8503
AAAI
AAAI
Existing conversational systems tend to generate generic responses. Recently, Background Based Conversations (BBCs) have been introduced to address this issue. Here, the generated responses are grounded in some background information. The proposed me
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5da1dfe4e76d4954919017350d62a1da
http://arxiv.org/abs/1908.06449
http://arxiv.org/abs/1908.06449
Autor:
Christof Monz, Marta R. Costa-jussà, Christian Federmann, Mark Fishel, Loïc Barrault, Mathias Müller, Philipp Koehn, Yvette Graham, Ondřej Bojar, Matthias Huck, Barry Haddow, Santanu Pal, Matt Post, Marcos Zampieri, Shervin Malmasi
Publikováno v:
WMT (2)
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
This paper presents the results of the premier shared task organized alongside the Conference on Machine Translation (WMT) 2019. Participants were asked to build machine translation systems for any of 18 language pairs, to be evaluated on a test set
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b3f9120f7bea1bc921105ebf0ccf446b
https://hdl.handle.net/11346/BIBLIO@id=-2735249752283795335
https://hdl.handle.net/11346/BIBLIO@id=-2735249752283795335
Publikováno v:
WWW
The Web Conference 2019: proceedings of the World Wide Web Conference WWW 2019 : May 13-17, 2019, San Francisco, CA, USA, 2879-2885
STARTPAGE=2879;ENDPAGE=2885;TITLE=The Web Conference 2019
The Web Conference 2019: proceedings of the World Wide Web Conference WWW 2019 : May 13-17, 2019, San Francisco, CA, USA, 2879-2885
STARTPAGE=2879;ENDPAGE=2885;TITLE=The Web Conference 2019
Sequence-to-Sequence (Seq2Seq) models have achieved encouraging performance on the dialogue response generation task. However, existing Seq2Seq-based response generation methods suffer from a low-diversity problem: they frequently generate generic re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::34c6f55f4377cf78ba01e5a7a047712e
https://doi.org/10.1145/3308558.3313415
https://doi.org/10.1145/3308558.3313415
Autor:
Christof Monz, Jerome R. Bellegarda
Publikováno v:
Computer Speech and Language, 35, 163-184. Academic Press Inc.
HighlightsThe purpose of this contribution is to review the state of the art in both areas, statistical methods and speech processing.Point out the top trends in statistical modelling across a wide range of problems and identify their most salient ch
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7d7fc5a14ae2289ec2fb4d907d3301c8
https://staff.science.uva.nl/c.monz/html/publications/csl2016.pdf
https://staff.science.uva.nl/c.monz/html/publications/csl2016.pdf
Autor:
Christof Monz, Varvara Logacheva, Barry Haddow, Lucia Specia, Christian Federmann, Rajen Chatterjee, Matt Post, Marco Turchi, Philipp Koehn, Matteo Negri, Matthias Huck, Qun Liu, Shujian Huang, Raphael Rubino, Yvette Graham, Ondřej Bojar
Publikováno v:
WMT
Bojar, Ondřej ORCID: 0000-0002-0606-0050, Chatterjee, Rajen, Federmann, Christian, Graham, Yvette, Haddow, Barry, Huang, Shujian, Huck, Matthias, Koehn, Philipp, Liu, Qun ORCID: 0000-0002-7000-1792 , Logacheva, Varvara, Monz, Christof, Negri, Matteo, Post, Matt, Rubino, Raphael, Specia, Lucia and Turchi, Marco (2017) Findings of the 2017 conference on machine translation (WMT17). In: Second Conference on Machine Translation (WMT17), 7-11 Sept 2017, Copenhagen, Denmark. ISBN 978-1-945626-96-8
Bojar, Ondřej ORCID: 0000-0002-0606-0050
This paper presents the results of the WMT17 shared tasks, which included three machine translation (MT) tasks (news, biomedical, and multimodal), two evaluation tasks (metrics and run-time estimation of MT quality), an automatic post-editing task, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c6cec3d8d0d7a5e1880aa956707250d6
https://hdl.handle.net/11346/BIBLIO@id=-2954443263314948582
https://hdl.handle.net/11346/BIBLIO@id=-2954443263314948582
Publikováno v:
EMNLP
Conference on Empirical Methods in Natural Language Processing: emnlp20017 : Copenhagen, Denmark, September 7-11, 2017 : conference proceedings, 1400-1410
STARTPAGE=1400;ENDPAGE=1410;TITLE=Conference on Empirical Methods in Natural Language Processing
Conference on Empirical Methods in Natural Language Processing: emnlp20017 : Copenhagen, Denmark, September 7-11, 2017 : conference proceedings, 1400-1410
STARTPAGE=1400;ENDPAGE=1410;TITLE=Conference on Empirical Methods in Natural Language Processing
Intelligent selection of training data has proven a successful technique to simultaneously increase training efficiency and translation performance for phrase-based machine translation (PBMT). With the recent increase in popularity of neural machine
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dab5724af8286393507ef927e9ab9491
https://doi.org/10.18653/v1/d17-1147
https://doi.org/10.18653/v1/d17-1147