Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Matthieu Labeau"'
Publikováno v:
Frontiers in Robotics and AI, Vol 9 (2022)
Socio-conversational systems are dialogue systems, including what are sometimes referred to as chatbots, vocal assistants, social robots, and embodied conversational agents, that are capable of interacting with humans in a way that treats both the sp
Externí odkaz:
https://doaj.org/article/a2f33d5e73af4cefa457f0f81ddcdd36
Publikováno v:
Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing.
In this paper, we place ourselves in a classification scenario in which the target classes and data type are not accessible during training. We use a meta-learning approach to determine whether or not meta-trained information from common social netwo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0ef3cba412098ccd09b752ca3c186ee1
https://doi.org/10.18653/v1/2021.metanlp-1.9
https://doi.org/10.18653/v1/2021.metanlp-1.9
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::494a35326050abd79a7468166bf582ea
https://doi.org/10.18653/v1/2021.emnlp-main.656
https://doi.org/10.18653/v1/2021.emnlp-main.656
Publikováno v:
Software Impacts. 12:100237
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f8b775516969cc9ccf00bbb8024d03d3
https://doi.org/10.1016/j.simpa.2022.100237
https://doi.org/10.1016/j.simpa.2022.100237
Publikováno v:
EMNLP (Findings)
Findings of the Association for Computational Linguistics: EMNLP 2020
Findings of the Association for Computational Linguistics: EMNLP 2020, Nov 2020, Online, France. pp.2636-2648, ⟨10.18653/v1/2020.findings-emnlp.239⟩
Findings of the Association for Computational Linguistics: EMNLP 2020
Findings of the Association for Computational Linguistics: EMNLP 2020, Nov 2020, Online, France. pp.2636-2648, ⟨10.18653/v1/2020.findings-emnlp.239⟩
Sequence labelling tasks like Dialog Act and Emotion/Sentiment identification are a key component of spoken dialog systems. In this work, we propose a new approach to learn generic representations adapted to spoken dialog, which we evaluate on a new
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3a7370e6ff25f33cf9610008606226d8
https://doi.org/10.18653/v1/2020.findings-emnlp.239
https://doi.org/10.18653/v1/2020.findings-emnlp.239
Publikováno v:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics, Nov 2020, Online, Dominican Republic. pp.7985-7993, ⟨10.18653/v1/2020.emnlp-main.641⟩
EMNLP (1)
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics, Nov 2020, Online, Dominican Republic. pp.7985-7993, ⟨10.18653/v1/2020.emnlp-main.641⟩
EMNLP (1)
While being an essential component of spoken language, fillers (e.g."um" or "uh") often remain overlooked in Spoken Language Understanding (SLU) tasks. We explore the possibility of representing them with deep contextualised embeddings, showing impro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::11f4a2b5a6b7ee34293e049558fb2561
Autor:
Matthieu Labeau, Shay B. Cohen
Publikováno v:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Nov 2019, Hong Kong, China. pp.4102-4112, ⟨10.18653/v1/D19-1421⟩
EMNLP/IJCNLP (1)
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Nov 2019, Hong Kong, China. pp.4102-4112, ⟨10.18653/v1/D19-1421⟩
EMNLP/IJCNLP (1)
Neural language models are usually trained using Maximum-Likelihood Estimation (MLE). The corresponding objective function for MLE is derived from the Kullback-Leibler (KL) divergence between the empirical probability distribution representing the da
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::20a7ccfbe0d4cc8af72f33310db57fe8
https://hal.archives-ouvertes.fr/hal-02912374
https://hal.archives-ouvertes.fr/hal-02912374
Autor:
Alexandre Allauzen, Matthieu Labeau
Publikováno v:
Proceedings of the First Workshop on Subword and Character Level Models in NLP
Proceedings of the First Workshop on Subword and Character Level Models in NLP, Sep 2017, Copenhagen, Denmark. pp.1-13, ⟨10.18653/v1/W17-4101⟩
SWCN@EMNLP
Proceedings of the First Workshop on Subword and Character Level Models in NLP, Sep 2017, Copenhagen, Denmark. pp.1-13, ⟨10.18653/v1/W17-4101⟩
SWCN@EMNLP
Most of neural language models use different kinds of embeddings for word prediction. While word embeddings can be associated to each word in the vocabulary or derived from characters as well as factored morphological decomposition, these word repres
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::50268d1ffc43ea420b4da332a9086579
https://hal.archives-ouvertes.fr/hal-02912377
https://hal.archives-ouvertes.fr/hal-02912377
Publikováno v:
WMT
This paper describes LIMSI's submissions to the news shared task at WMT'17 for English into Czech and Latvian, as well as related experiments. This year's novelties consist in the use of a neural machine translation system with a factored output pred
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5524e27a4f1738ecdfe60057ab4505db
https://doi.org/10.18653/v1/w17-4721
https://doi.org/10.18653/v1/w17-4721
Autor:
Matthieu Labeau, Alexandre Allauzen
Publikováno v:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
15th Conference of the European Chapter of the Association for Computational Linguistics
15th Conference of the European Chapter of the Association for Computational Linguistics:, Apr 2017, Valencia, Spain. pp.15-20
EACL (2)
15th Conference of the European Chapter of the Association for Computational Linguistics
15th Conference of the European Chapter of the Association for Computational Linguistics:, Apr 2017, Valencia, Spain. pp.15-20
EACL (2)
International audience; Noise Contrastive Estimation (NCE) is a learning procedure that is regularly used to train neural language models, since it avoids the computational bottleneck caused by the output softmax. In this paper , we attempt to explai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::234eab320ace6695cbf264bc3d2d9a82
https://hal.science/hal-02912384
https://hal.science/hal-02912384