Teach Your Robot Your Language! Trainable Neural Parser for Modelling Human Sentence Processing: Examples for 15 Languages
Résumé
We present a Recurrent Neural Network (RNN) that performs thematic role assignment and can be used for Human-Robot Interaction (HRI). The RNN is trained to map sentence structures to meanings (e.g. predicates). Previously, we have shown that the model is able to generalize on English and French corpora. In this study, we investigate its ability to adapt to various languages originating from Asia or Europe. We show that it can successfully learn to parse sentences related to home scenarios in fifteen languages: English, German, French, Spanish, Catalan, Basque, Portuguese, Italian, Bulgarian, Turkish, Persian, Hindi, Marathi, Malay and Mandarin Chinese. Moreover, in the corpora we have deliberately included variable complex sentences in order to explore the flexibility of the predicate-like output representations. This demonstrates that (1) the learning principle of our model is not limited to a particular language (or particular sentence structures), but more generic in nature, and (2) it can deal with various kind of representations (not only predicates), which enables users to adapt it to their own needs. As the model is inspired from neuroscience and language acquisition theories, this generic and language independent aspect makes it a good candidate for modelling human sentence processing. It is especially relevant when this model is implemented in grounded multimodal robotic architectures.