Výsledky vyhledávání - "Christine Jacquin"

Towards Simple but Efficient Next Utterance Ranking

Autor: Nicolas Hernandez, Basma El Amel Boussaha, Emmanuel Morin, Christine Jacquin

Publikováno v: 20th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing)
20th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing), Apr 2019, La Rochelle, France

Retrieval-based dialogue systems converse with humans by ranking candidate responses according to their relevance to the history of the conversation (context). Recent studies either match the context with the response on only sequence level or use co

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::66d5f994d803c75ba63e5bb48babe28a
https://hal.archives-ouvertes.fr/hal-02073275

Zobrazit plný text záznamu

Transcription automatique et segmentation thématique de livres d’heures manuscrits

Autor: Béatrice Daille, Amir Hazem, Christopher Kermorvant, Martin Maarand, Marie-Laurence Bonhomme, Dominique Stutzmann, Jacob Currie, Christine Jacquin

Publikováno v: Revue TAL
Revue TAL, ATALA (Association pour le Traitement Automatique des Langues), 2019, TAL et humanités numériques, 60 (3), pp.13-36
HAL

International audience; Books of Hours are the number one best seller of the Middle Ages, with more than 10 000 copies preserved. They are a crucial witness to the medieval mindset, but their textual contents have been very scarcely studied. They are

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::70792991b1ac05eec2e9f1520cb17d14
http://hal.univ-nantes.fr/hal-02430291

Zobrazit plný text záznamu

Towards Automatic Variant Analysis of Ancient Devotional Texts

Autor: Béatrice Daille, Jacob Currie, Amir Hazem, Dominique Stutzmann, Christine Jacquin

Publikováno v: 1st International Workshop on Computational Approaches to Historical Language Change
1st International Workshop on Computational Approaches to Historical Language Change, co-located with ACL 2019, Aug 2019, Florence, Italy. pp.240-249, ⟨10.18653/v1/W19-4730⟩

We address in this paper the issue of text reuse in liturgical manuscripts of the middle ages. More specifically, we study variant readings of the Obsecro Te prayer, part of the devotional Books of Hours often used by Christians as guidance for their

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4a8697655aa2b5b03dd74590548eef03
https://doi.org/10.18653/v1/w19-4730

Zobrazit plný text záznamu

End-to-end response selection based on multi-level context response matching

Autor: Christine Jacquin, Nicolas Hernandez, Emmanuel Morin, Basma El Amel Boussaha

Publikováno v: Computer Speech & Language. 63:101080

This paper presents our work on the Dialog System Technology Challenges 7 (DSTC7). We took part in Track 1 on sentence selection which evaluates response retrieving in dialog systems on more realistic test scenarios compared to the state-of-the-art e

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::fd35c0c04a1f2d119bf6c4be0a04cf78
https://doi.org/10.1016/j.csl.2020.101080

Zobrazit plný text záznamu

De la gestion locale à la recherche distribuée dans des sources d'informations et de connaissances

Autor: Philippe Lamarre, Sylvie Cazalens, Emmanuel Desmontils, Christine Jacquin

Publikováno v: L'objet. 8:47-69

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::6a937ce2319643899651f4acf2dbd23c
https://doi.org/10.3166/objet.8.4.47-69

Zobrazit plný text záznamu

Incorporating named entity recognition into the speech transcription process

Autor: Sylvain Meignier, Christine Jacquin, Mohamed Hatmi, Emmanuel Morin

Publikováno v: INTERSPEECH
Interspeech 2013
Interspeech
Interspeech, 2013, Lyon, France
Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech'13)
Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech'13), Aug 2013, Lyon, France. pp.3732-3736

International audience; Named Entity Recognition (NER) from speech usually involves two sequential steps: transcribing the speech using Automatic Speech Recognition (ASR) and annotating the outputs of the ASR process using NER techniques. Recognizing

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4ef05fb6d26dc5afba460903ff26cc81
https://doi.org/10.21437/interspeech.2013-588

Zobrazit plný text záznamu

Clustering Short Text and Its Evaluation

Autor: Prajol Shrestha, Christine Jacquin, Béatrice Daille

Publikováno v: Computational Linguistics and Intelligent Text Processing ISBN: 9783642286001
CICLing (2)

Recently there has been an increase in interest towards clustering short text because it could be used in many NLP applications. According to the application, a variety of short text could be defined mainly in terms of their length (e.g. sentence, pa

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::ee48618f41496be3783bc1bb6bd3171c
https://doi.org/10.1007/978-3-642-28601-8_15

Zobrazit plný text záznamu

Automatic named identification of speakers using diarization and ASR systems

Autor: Yannick Estève, Sylvain Meignier, Simon Petitrenaud, Vincent Jousse, Christine Jacquin

Publikováno v: ICASSP

In this paper, we consider the extraction of speaker identity from audio records of broadcast news without a priori acoustic information about speakers. Using an automatic speech recognition system and an automatic speaker diarization system, we pres

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::bb19020fd77ede20cf62accb190eadfd
https://doi.org/10.1109/icassp.2009.4960644

Zobrazit plný text záznamu

The Answer Validation System ProdicosAV Dedicated to French

Autor: Laura Monceaux, Emmanuel Desmontils, Christine Jacquin

Publikováno v: Lecture Notes in Computer Science ISBN: 9783642044465
CLEF

In this paper, we present the ProdicosAV answer validation system which was developed by the NLP team from the LINA institute. ProdicosAV system is based on the Prodicos System which participated two years ago in the Question Answering CLEF evaluatio

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9139e671bc33314d5d562cb7cebc8c7d
https://doi.org/10.1007/978-3-642-04447-2_54

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání