1 |
Contribution d'informations syntaxiques aux capacités de généralisation compositionelle des modèles seq2seq convolutifs
|
|
|
|
In: Actes de la 28e Conférence sur le Traitement Automatique des Langues Naturelles. Volume 1 : conférence principale ; Traitement Automatique des Langues Naturelles ; https://hal.archives-ouvertes.fr/hal-03265890 ; Traitement Automatique des Langues Naturelles, 2021, Lille, France. pp.134-141 (2021)
|
|
BASE
|
|
Show details
|
|
2 |
Catplayinginthesnow: Impact of Prior Segmentation on a Model of Visually Grounded Speech
|
|
|
|
In: Conference on Natural Language Learning (CoNLL) ; https://hal.archives-ouvertes.fr/hal-02962275 ; Conference on Natural Language Learning (CoNLL), Nov 2020, Virtual, France (2020)
|
|
BASE
|
|
Show details
|
|
3 |
MaSS: A Large and Clean Multilingual Corpus of Sentence-aligned Spoken Utterances Extracted from the Bible
|
|
|
|
In: Proceedings of The 12th Language Resources and Evaluation Conference ; https://hal.archives-ouvertes.fr/hal-02611059 ; Proceedings of The 12th Language Resources and Evaluation Conference, May 2020, Marseille, France. pp.6486 - 6493 (2020)
|
|
BASE
|
|
Show details
|
|
4 |
Catplayinginthesnow: Impact of Prior Segmentation on a Model of Visually Grounded Speech ...
|
|
|
|
Abstract:
The language acquisition literature shows that children do not build their lexicon by segmenting the spoken input into phonemes and then building up words from them, but rather adopt a top-down approach and start by segmenting word-like units and then break them down into smaller units. This suggests that the ideal way of learning a language is by starting from full semantic units. In this paper, we investigate if this is also the case for a neural model of Visually Grounded Speech trained on a speech-image retrieval task. We evaluated how well such a network is able to learn a reliable speech-to-image mapping when provided with phone, syllable, or word boundary information. We present a simple way to introduce such information into an RNN-based model and investigate which type of boundary is the most efficient. We also explore at which level of the network's architecture such information should be introduced so as to maximise its performances. Finally, we show that using multiple boundary types at once in a ... : Accepted at CoNLL20 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2006.08387 https://arxiv.org/abs/2006.08387
|
|
BASE
|
|
Hide details
|
|
5 |
Word Recognition, Competition, and Activation in a Model of Visually Grounded Speech
|
|
|
|
In: Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL) ; https://hal.archives-ouvertes.fr/hal-02359540 ; Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), Nov 2019, Hong Kong, China. pp.339-348, ⟨10.18653/v1/K19-1032⟩ (2019)
|
|
BASE
|
|
Show details
|
|
6 |
Models of Visually Grounded Speech Signal Pay Attention to Nouns: A Bilingual Experiment on English and Japanese
|
|
|
|
In: International Conference on Acoustics, Speech and Signal Processing (ICASSP) ; https://hal.archives-ouvertes.fr/hal-02013984 ; International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2019, Brighton, United Kingdom. pp.8618-8622, ⟨10.1109/ICASSP.2019.8683069⟩ (2019)
|
|
BASE
|
|
Show details
|
|
7 |
MaSS - Multilingual corpus of Sentence-aligned Spoken utterances ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
MaSS - Multilingual corpus of Sentence-aligned Spoken utterances ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Word Recognition, Competition, and Activation in a Model of Visually Grounded Speech ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Models of Visually Grounded Speech Signal Pay Attention To Nouns: a Bilingual Experiment on English and Japanese ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Emergence of attention in a neural model of visually grounded speech
|
|
|
|
In: Learning Language in Humans and in Machines 2018 conference ; https://hal.archives-ouvertes.fr/hal-01970514 ; Learning Language in Humans and in Machines 2018 conference, Jul 2018, Paris, France (2018)
|
|
BASE
|
|
Show details
|
|
16 |
SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|