From Phonemes to Sentence Comprehension: A Neurocomputational Model of Sentence Processing for Robots

Xavier Hinaut 1
1 Mnemosyne - Mnemonic Synergy
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, IMN - Institut des Maladies Neurodégénératives [Bordeaux]
Abstract : There has been an important progress these last years in speech recognition systems. The word recognition error rate went down with the arrival of deep learning methods. However, if one uses cloud speech API and integrate it inside a robotic architecture, one faces a non negligible number of wrong sentence recognition. Thus speech recognition can not be considered as solved (because many sentences out of their contexts are ambiguous). We believe that contextual solutions (i.e. adaptable and trainable on different HRI applications) have to be found. In this perspective, the way children learn language and how our brains process utterances may help us improve how robots process language. Getting inspiration from language acquisition theories and how the brain processes sentences we previously developed a neuro-inspired model of sentence processing. In this study, we investigate how this model can process different levels of abstractions as input: sequence of phonemes, seq. of words or grammatical constructions. We see that even if the model was only tested on grammatical constructions before, it has better performances with words and phonemes inputs.
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.inria.fr/hal-01964524
Contributor : Xavier Hinaut <>
Submitted on : Thursday, January 3, 2019 - 11:17:04 AM
Last modification on : Thursday, February 7, 2019 - 3:36:51 PM
Long-term archiving on : Thursday, April 4, 2019 - 1:21:07 PM

File

2018-05_Paris_ws_neurorob-IA_0...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01964524, version 1

Citation

Xavier Hinaut. From Phonemes to Sentence Comprehension: A Neurocomputational Model of Sentence Processing for Robots. SBDM2018 Satellite-Workshop on interfaces between Robotics, Artificial Intelligence and Neuroscience, May 2018, Paris, France. ⟨hal-01964524⟩

Share

Metrics

Record views

84

Files downloads

145