1 |
Cross-lingual and cross-domain evaluation of Machine Reading Comprehension with Squad and CALOR-Quest corpora
|
|
|
|
In: Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020) ; LREC 2020 ; https://hal.archives-ouvertes.fr/hal-02973245 ; LREC 2020, May 2020, MARSEILLE, France. pp.5491-5497 ; https://lrec2020.lrec-conf.org/en/ (2020)
|
|
BASE
|
|
Show details
|
|
2 |
Analyse sémantique robuste par apprentissage antagoniste pour la généralisation de domaine
|
|
|
|
In: Actes de la 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 4 : Démonstrations et résumés d'articles internationaux ; 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 4 : Démonstrations et résumés d'articles internationaux ; https://hal.archives-ouvertes.fr/hal-02768521 ; 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 4 : Démonstrations et résumés d'articles internationaux, 2020, Nancy, France. pp.71-72 (2020)
|
|
BASE
|
|
Show details
|
|
3 |
Adapting a FrameNet Semantic Parser for Spoken Language Understanding Using Adversarial Learning
|
|
|
|
In: Interspeech 2019 ; https://hal.archives-ouvertes.fr/hal-02298417 ; Interspeech 2019, Sep 2019, Graz, Austria. pp.799-803, ⟨10.21437/Interspeech.2019-2732⟩ (2019)
|
|
BASE
|
|
Show details
|
|
4 |
Robust Semantic Parsing with Adversarial Learning for Domain Generalization
|
|
|
|
In: Proceedings of the 2019 Conference of the North ; https://hal.archives-ouvertes.fr/hal-02298402 ; Proceedings of the 2019 Conference of the North, Jun 2019, Minneapolis - Minnesota, France. pp.166-173, ⟨10.18653/v1/N19-2021⟩ (2019)
|
|
BASE
|
|
Show details
|
|
5 |
The Impact of Word Representations on Sequential Neural MWE Identification
|
|
|
|
In: Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019) ; Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019) ; https://hal.archives-ouvertes.fr/hal-02318287 ; Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019), Aug 2019, Florence, Italy. pp.169 - 175, ⟨10.18653/v1/W19-5121⟩ (2019)
|
|
BASE
|
|
Show details
|
|
6 |
Robust Semantic Parsing with Adversarial Learning for Domain Generalization ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Adapting a FrameNet Semantic Parser for Spoken Language Understanding Using Adversarial Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Handling Normalization Issues for Part-of-Speech Tagging of Online Conversational Text
|
|
|
|
In: LREC proceedings ; Eleventh International Conference on Language Resources and Evaluation (LREC 2018) ; https://hal.archives-ouvertes.fr/hal-01943391 ; Eleventh International Conference on Language Resources and Evaluation (LREC 2018), 2018, Miyazaki, Japan (2018)
|
|
BASE
|
|
Show details
|
|
9 |
Prédiction de l'échec d'une conversation médiée dans un contexte de dialogues à rôles asymétriques
|
|
|
|
In: Vingt-cinquième conférence sur le Traitement Automatique des Langues Naturelles (TALN) ; https://hal.archives-ouvertes.fr/hal-01798604 ; Vingt-cinquième conférence sur le Traitement Automatique des Langues Naturelles (TALN), ATALA, May 2018, Rennes, France (2018)
|
|
BASE
|
|
Show details
|
|
10 |
Automatic transcription error recovery for Person Name Recognition
|
|
|
|
In: Interspeech 2012 ; https://hal.archives-ouvertes.fr/hal-02356295 ; Interspeech 2012, Sep 2012, Portland, United States (2012)
|
|
BASE
|
|
Show details
|
|
11 |
Detecting Person Presence in TV Shows with Linguistic and Structural Features
|
|
|
|
In: IEEE International Conference in Acoustics, Speech and Signal Processing (ICASSP), Kyoto (Japan) ; https://hal-amu.archives-ouvertes.fr/hal-01194256 ; IEEE International Conference in Acoustics, Speech and Signal Processing (ICASSP), Kyoto (Japan), 2012, Unknown, Unknown Region (2012)
|
|
BASE
|
|
Show details
|
|
13 |
Automatic customer feedback processing: alarm detection in open question spoken messages
|
|
|
|
In: Interspeech ; https://hal.archives-ouvertes.fr/hal-01314565 ; Interspeech, Sep 2008, brisbane, Australia (2008)
|
|
BASE
|
|
Show details
|
|
15 |
SPOKEN LANGUAGE UNDERSTANDING STRATEGIES ON THE FRANCE TELECOM 3000 VOICE AGENCY CORPUS Ge'raldine Damnati1, Fre'deric Bechet2
|
|
|
|
In: IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07 ; https://hal.archives-ouvertes.fr/hal-01317193 ; IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07 , Apr 2007, Honolulu, United States (2007)
|
|
BASE
|
|
Show details
|
|
16 |
Experiments on the France Telecom 3000 Voice Agency corpus: academic research on an industrial spoken dialog system
|
|
|
|
In: NAACL-HLT-Dialog '07 ; https://hal.archives-ouvertes.fr/hal-01317176 ; NAACL-HLT-Dialog '07, Apr 2007, Rochester, United States (2007)
|
|
BASE
|
|
Show details
|
|
17 |
Conditional use of Word Lattices, Confusion Networks and 1-best string hypotheses in a Sequential Interpretation Strategy
|
|
|
|
In: Interspeech ; https://hal.archives-ouvertes.fr/hal-01312935 ; Interspeech, Aug 2007, Anvers, Belgium (2007)
|
|
Abstract:
International audience ; Within the context of a deployed spoken dialog service, this study presents a new interpretation strategy based on the sequential use of different ASR output representations: 1-best strings, word lattices and confusion networks. The goal is to reject as early as possible in the decoding process the non-relevant messages containing non-speech or out-of-domain content. This is done through the 1-pass of the ASR decoding process thanks to specific acoustic and language models. A confusion network (CN) is then calculated for the remaining messages and another rejection process is applied with the confidence measures obtained in the CN. The messages kept at this stage are considered relevant; therefore the search for the best interpretation is applied to a richer search space than just the 1-best word string: either the whole CN or the whole word lattice. An improved, SLU oriented, CN generation algorithm is also proposed that significantly reduces the size of the CN obtained while improving the recognition performance. This strategy is evaluated on a large corpus of real users' messages obtained from a deployed service.
|
|
Keyword:
[INFO]Computer Science [cs]; Confusion Networks; Decision Strategy; Index Terms: Spoken Language Understanding; Lattice Decoding
|
|
URL: https://hal.archives-ouvertes.fr/hal-01312935
|
|
BASE
|
|
Hide details
|
|
|
|