, Cet arbre correspond à la phrases "X-name is an Italian restaurant by the river". La représentation arborescente est d'abord convertie dans une chaîne des caractères à l'aide des parenthèses : (<root> <root> ((X-name n :subj) be v : fin ((Italian adj :attr) restaurant n :obj

, Pour pénaliser le système pour les sorties qui manquent ou ajoutent les informations, ils utilisent un LSTM RNN classifieur qui prend en entrée cette phrase prédite et qui détermine s'il y a des omissions ou ajouts des slots par rapport à la représentation sémantique de source, Cette représentation est passé au modèle LSTM RNN du type seq2seq

, Nous avons aussi découvert que la présence de l'intention semble ne pas avoir d'influence sur la prédiction des slots par Tf-seq2seq. En ce qui concerne son mode mot vs caractère, la performance du modèle à caractères est pis sur les intentions mais elle est mieux

A. Bibliographie, M. Agarwal, A. Barham, P. Brevdo, E. Chen et al., TensorFlow : Large-scale machine learning on heterogeneous systems. Software available from tensorflow.org, 2015.

A. , S. Et, D. , and M. , A surprisingly effective out-of-the-box char2char model on the e2e nlg challenge dataset, Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pp.158-163, 2017.

A. and F. , Reconnaissance automatique de la parole de personnes âgées pour les services d'assistance à domicile. Traitement du signal et de l'image, 2014.

A. , A. Makhoul, and R. S. , Automatic modeling for adding new words to a large-vocabulary continuous speech recognition system, Proceedings of the Acoustics, Speech, and Signal Processing, pp.305-308, 1991.

B. , R. Canavesio, F. Et, R. , and C. , Automation of telecom italia directory assistance service : field trial results, Interactive Voice Technology for Telecommunications Applications, 1998. IVTTA '98. Proceedings. 1998 IEEE 4th Workshop, pp.11-16, 1998.

B. , S. Klein, E. Loper, and E. , Natural Language Processing with Python, 2009.

B. , H. Quignard, M. Et, D. , and A. , Media : a semantically annotated corpus of task oriented dialogs in french. results of the french media evaluation campaign, Language Resources and Evaluation, vol.43, issue.4, pp.329-354, 2009.
URL : https://hal.archives-ouvertes.fr/inria-00424619

B. , A. Et, W. , and J. , Learning end-to-end goal-oriented dialog, 2016.

D. Braun, A. Hernandez-mendez, F. Matthes, L. Et, and M. , Evaluating natural language understanding services for conversational question answering systems, Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, 2017.
DOI : 10.18653/v1/w17-5522

URL : https://doi.org/10.18653/v1/w17-5522

B. , D. , G. , A. Luong, T. Et et al., Massive Exploration of Neural Machine Translation Architectures, 2017.

B. , J. Murveit, H. Shriberg, E. Et, P. et al., Modeling spontaneous speech effects in large vocabulary speech recognition applications, Speech and Natural Language Workshop, 1992.

C. , Z. Et, L. , and R. , Designing smart home interfaces for the elderly, SIGACCESS Accessibility and Computing, vol.95, pp.10-16, 2009.

C. , M. Estève, D. Escriba, C. Et, C. et al., A review of smart homes-present state and future challenges, Computer Methods and Programs in Biomedicine, vol.91, issue.1, pp.55-81, 2008.

C. , W. Jaitly, N. Le, Q. V. Vinyals, and O. , Listen, attend and spell, 2015.

C. , K. Van, M. , B. Gülçehre, Ç. Bougares et al., Learning phrase representations using RNN encoder-decoder for statistical machine translation, 2014.

C. , J. Gülçehre, Ç. Cho, K. Bengio, and Y. , Empirical evaluation of gated recurrent neural networks on sequence modeling, 2014.

C. , M. G. , A. , and J. F. , Coding dialogs with the damsl annotation scheme, 1997.

C. , C. Vapnik, and V. , Support-vector networks, Machine Learning, pp.273-297, 1995.

C. and D. , A Dictionary of Linguistics and Phonetics. The Language Library, 2011.

D. , O. Et, J. , and F. , Sequence-to-sequence generation for spoken dialogue via deep syntax trees and strings, 2016.

G. and K. , An Introduction to Neural Networks, 1997.

H. E. , Y. Et, Y. , and S. , A data-driven spoken language understanding system, 2003 IEEE Workshop on Automatic Speech Recognition and Understanding, pp.583-588, 2003.

H. , C. T. Godfrey, J. J. Doddington, and G. R. , The atis spoken language systems pilot corpus, Proceedings of the Workshop on Speech and Natural Language, HLT '90, pp.96-101, 1990.

H. , I. L. Et, Z. , and V. W. , New words : implications for continuous speech recognition, Third European Conference on Speech Communication and Technology, 1993.

H. , L. Sil, A. , J. I. , H. Et et al., Improving slot filling performance with attentive neural networks on dependency structures, 2017.

J. , M. Lee, and G. G. , Triangular-chain conditional random fields, IEEE Transactions on Audio, Speech, and Language Processing, vol.16, issue.7, pp.1287-1302, 2008.

J. I. , Y. Haffari, G. Et, E. , and J. , A latent variable recurrent neural network for discourse relation language models, 2016.

K. , N. Et, B. , and P. , Recurrent convolutional neural networks for discourse compositionality, 2013.

K. , T. Et, V. , and K. , Evolution towards smart home environments : Empirical evaluation of three user interfaces, Personal Ubiquitous Comput, vol.8, issue.3-4, pp.234-240, 2004.

L. , J. D. Mccallum, A. Pereira, and F. C. , Conditional random fields : Probabilistic models for segmenting and labeling sequence data, Proceedings of the Eighteenth International Conference on Machine Learning, ICML '01, pp.282-289, 2001.

L. , F. Mostefa, D. Besacier, L. Estève, Y. Quignard et al., Leveraging study of robustness and portability of spoken language understanding systems across languages and domains : the PORTMEDIA corpora, LREC, pp.1436-1442, 2012.
URL : https://hal.archives-ouvertes.fr/hal-00683433

L. , B. Et, L. , and I. , Attention-based recurrent neural network models for joint intent detection and slot filling, 2016.

L. , B. Et, L. , and I. , An end-to-end trainable neural network model with belief tracking for task-oriented dialog, 2017.

M. , E. Jabaian, B. Huet, S. Lefevre, and F. , Automatic corpus extension for data-driven natural language generation, Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC, 2016.
URL : https://hal.archives-ouvertes.fr/hal-02021894

M. , G. Dauphin, Y. Yao, K. Bengio, Y. Deng et al., Using recurrent neural networks for slot filling in spoken language understanding, Transactions on Audio, Speech, and Language Processing, vol.23, issue.3, pp.530-539, 2015.

M. , T. Sutskever, I. Chen, K. Corrado, G. Dean et al., Distributed representations of words and phrases and their compositionality. CoRR, abs/1310, p.4546, 2013.

M. , S. Gödde, F. Et, W. , M. ;. Choukri et al., Corpus analysis of spoken smart-home interactions with older users, éditeurs : Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), 2008.

N. , J. Du?ek, O. Et, R. , and V. , The E2E dataset : New challenges for end-toend generation, Proceedings of the 18th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2017.

P. , R. Tzoukermann, E. Gorelov, Z. Levin, E. Gauvain et al., A speech understanding system based on statistical representation of semantics, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp.193-196, 1992.

P. , O. Hastie, and H. , A survey on metrics for the evaluation of user simulations, Knowledge Engineering Review, vol.28, issue.01, pp.59-73, 2013.
URL : https://hal.archives-ouvertes.fr/hal-00771654

P. , F. Vacher, M. Golanski, C. Roux, C. Et et al., Design and evaluation of a smart home voice interface for the elderly : Acceptability and objection aspects, Personal Ubiquitous Comput, vol.17, issue.1, pp.127-144, 2013.
URL : https://hal.archives-ouvertes.fr/hal-00953242

R. and S. , Natural language understanding for smarthomes, 2017.

R. , A. Langner, B. Bohus, D. Black, A. W. Et et al., Let's go public ! taking a spoken dialog system to the real world, INTERSPEECH 2005-Eurospeech, 9th European Conference on Speech, Communication and Technology, pp.885-888, 2005.

R. , S. V. Et, S. , and A. , Recurrent neural network and lstm models for lexical utterance classification, INTERSPEECH, pp.135-139, 2015.

R. , P. Et, L. , and J. , Evaluation of NLP Systems, The Handbook of Computational Linguistics and Natural Language Processing, 2010.

R. , S. Vacher, M. Et, P. , and F. , Documentation interne du projet ANR VocADom, 2018.

R. , A. I. Thayer, E. H. Constantinides, P. C. Tchou, C. Shern et al., Creating natural dialogs in the carnegie mellon communicator system, Sixth European Conference on Speech Communication and Technology, 1999.

S. and S. , Tina : A natural language system for spoken language applications, Comput. Linguist, vol.18, issue.1, pp.61-86, 1992.

S. , I. V. Lowe, R. Henderson, P. Charlin, L. Pineau et al., A survey of available corpora for building data-driven dialogue systems, CoRR, 2015.

A. Stubbs, P. Et, and J. , Natural Language Annotation for Machine Learning, 2012.

S. , I. Vinyals, O. Et, L. E. , and Q. V. , Sequence to sequence learning with neural networks, 2014.

T. , Q. H. Zukerman, I. Et, H. , and G. , Preserving distributional information in dialogue act classification, Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp.2151-2156, 2017.

T. , D. R. Heeman, P. A. Maier, E. Mast, M. Et et al., Utterance units in spoken dialogue, éditeurs : Dialogue Processing in Spoken Language Systems, ECAI'96 Workshop, vol.1236, pp.125-140, 1996.

T. , G. De-mori, and R. , Spoken Language Understanding Systems for Extracting Semantic Information from Speech, 2011.

T. , G. Hakkani-tür, D. Heck, and L. , What's left to be understood in ATIS ?, IEEE Workshop on Spoken Language Technologies, 2010.

M. Vacher, Projet ANR VocADom-Livrable C5.1-Corpus sonore et multimodal d'évaluation, 2018.

M. Vacher, S. Caffiau, F. Portet, B. Meillon, C. Roux et al., Evaluation of a context-aware voice interface for ambient assisted living : qualitative user study vs. quantitative system evaluation, ACM Transactions on Accessible Computing, vol.7, issue.2, p.36, 2015.
URL : https://hal.archives-ouvertes.fr/hal-01138090

M. Vacher, B. Lecouteux, P. Chahuara, F. Portet, B. Meillon et al., The Sweet-Home speech and multimodal corpus for home automation interaction, The 9th edition of the Language Resources and Evaluation Conference (LREC), pp.4499-4506, 2014.
URL : https://hal.archives-ouvertes.fr/hal-00953006

W. , M. A. Passonneau, R. Boland, and J. E. , Quantitative and qualitative evaluation of darpa communicator spoken dialogue systems, Proceedings of the 39th Annual Meeting on Association for Computational Linguistics, ACL '01, pp.515-522, 2001.

W. and R. S. , The Anatomy of, pp.181-210, 2009.

W. , Y. Deng, L. Et, A. , and A. , Spoken language understanding-an introduction to the statistical framework, IEEE Signal Processing Magazine, vol.22, pp.16-31, 2005.

W. and W. , Modelling non-verbal sounds for speech recognition, Proceedings of the Workshop on Speech and Natural Language, HLT '89, pp.47-50, 1989.

W. and W. , The cmu air travel information service : Understanding spontaneous speech, Proceedings of the Workshop on Speech and Natural Language, HLT '90, pp.127-129, 1990.

W. and W. , Understanding spontaneous speech : the phoenix system, [Proceedings] ICASSP 91 : 1991 International Conference on Acoustics, Speech, and Signal Processing, vol.1, pp.365-367, 1991.

W. and J. , Eliza&mdash ;a computer program for the study of natural language communication between man and machine, Commun. ACM, vol.9, issue.1, pp.36-45, 1966.

W. , J. D. Raux, A. Henderson, and M. , The dialog state tracking challenge series : A review, D&D, vol.7, issue.3, pp.4-33, 2016.

W. Yi, Y. Et, A. , and A. , Discriminative models for spoken language understanding, 2006.

Y. , S. Ga?i´cga?i´-ga?i´c, M. Thomson, B. Et, W. et al., Pomdp-based statistical spoken dialog systems : A review, Proceedings of the IEEE, vol.101, issue.5, pp.1160-1179, 2013.

Y. U. , Z. Black, A. W. Et, R. , and A. I. , Learning conversational systems that interleave task and non-task content, 2017.

Y. U. , Z. Bohus, D. Et, H. , and E. , Incremental coordination : Attention-centric speech production in a physically situated conversational agent, The 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp.402-406, 2015.

Z. , X. Et, W. , and H. , A joint model of intent determination and slot filling for spoken language understanding, Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI'16, pp.2993-2999, 2016.

Z. , V. Seneff, S. Polifroni, J. Phillips, M. S. Pao et al., PEGASUS : A spoken dialogue interface for on-line air travel planning, Speech Communication, vol.15, issue.3-4, pp.331-340, 1994.