M. H. Christiansen, Creating language: Integrating evolution, acquisition, and processing, 2016.

I. Sutskever, Sequence to sequence learning with neural networks, NIPS, pp.3104-3112, 2014.

, The word feedback could be misleading because already used in Reservoir Computing terminology. Thus, we replace the word feedback by backwards in the following discussion

D. Bahdanau, Neural machine translation by jointly learning to align and translate, 2014.

A. Vaswani, Attention is all you need, NIPS, pp.5998-6008, 2017.

X. Hinaut, Exploring the acquisition and production of grammatical constructions through human-robot interaction with echo state networks, Frontiers in Neurorobotics, vol.8, 2014.
URL : https://hal.archives-ouvertes.fr/hal-02383530

J. , Using Natural Language Feedback in a Neuro-inspired Integrated Multimodal Robotic Architecture, Proc. of RO-MAN, 2016.

X. Hinaut and J. Twiefel, Teach your robot your language! trainable neural parser for modelling human sentence processing: Examples for 15 languages, IEEE TCDS, 2019.
URL : https://hal.archives-ouvertes.fr/hal-01665807

J. Hatori, Interactively picking real-world objects with unconstrained spoken language instructions, IEEE ICRA, 2018.

F. Triefenbach, Acoustic modeling with hierarchical reservoirs, IEEE Transactions on Audio, Speech, and Language Processing, vol.21, issue.11, pp.2439-2450, 2013.

A. Graves, Speech recognition with deep recurrent neural networks, IEEE ICASSP, pp.6645-6649, 2013.

J. K. Chorowski, Attention-based models for speech recognition, NIPS, pp.577-585, 2015.

N. T. Markov and H. Kennedy, The importance of being hierarchical, Current Opinion in Neurobiology, vol.23, issue.2, pp.187-194, 2013.

J. Schmidhuber, Learning complex, extended sequences using the principle of history compression, Neural Computation, vol.4, issue.2, pp.234-242, 1992.

S. E. Hihi and Y. Bengio, Hierarchical recurrent neural networks for long-term dependencies, NIPS, pp.493-499, 1995.

M. Hermans and B. Schrauwen, Training and analysing deep recurrent neural networks, NIPS, pp.190-198, 2013.

C. Gallicchio, Deep reservoir computing: a critical experimental analysis, Neurocomputing, vol.268, pp.87-99, 2017.

C. Gallicchio, Design of deep echo state networks, Neural Networks, vol.108, pp.33-47, 2018.

D. Verstraeten, An experimental unification of reservoir computing methods, Neural Networks, vol.20, issue.3, pp.391-403, 2007.

M. Luko?evi?ius and H. Jaeger, Reservoir computing approaches to recurrent neural network training, Computer Science Review, vol.3, issue.3, pp.127-149, 2009.

F. Triefenbach, Phoneme recognition with large hierarchical reservoirs, NIPS, pp.2307-2315, 2010.

J. Garofolo, Timit acoustic-phonetic continuous speech corpus, Linguistic Data Consortium LDC93S1, 1993.

H. Jaeger, The "echo state" approach to analysing and training recurrent neural networks, 2001.

H. Jaeger, Optimization and applications of echo state networks with leaky-integrator neurons, Neural Networks, vol.20, issue.3, pp.335-352, 2007.

H. Jaeger and H. Haas, Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication, Science, vol.304, issue.5667, pp.78-80, 2004.

C. Gallicchio, Chasing the echo state property, ESANN, 2018.

C. Gallicchio and A. Micheli, Echo state property of deep reservoir computing networks, Cognitive Computation, vol.9, issue.3, pp.337-350, 2017.

J. , Syntactic reanalysis in language models for speech recognition, IEEE ICDL-EpiRob, 2017.

X. Hinaut and P. Dominey, Real-time parallel processing of grammatical structure in the fronto-striatal system: a recurrent network simulation study using reservoir computing, PLoS ONE, vol.8, issue.2, p.52946, 2013.
URL : https://hal.archives-ouvertes.fr/hal-01968923

X. Hinaut, Which input abstraction is better for a robot syntax acquisition model? phonemes, words or grammatical constructions?, IEEE ICDL-EpiRob, 2018.
URL : https://hal.archives-ouvertes.fr/hal-01889919

X. Hinaut and M. Spranger, Learning to parse grounded language using reservoir computing, IEEE ICDL-EpiRob, 2019.
URL : https://hal.archives-ouvertes.fr/hal-02422157

A. Hanuschkin, A hebbian learning rule gives rise to mirror neurons and links them to control theoretic inverse models, Frontiers in Neural Circuits, vol.7, 2013.

Z. Huang, Bidirectional LSTM-CRF models for sequence tagging, 2015.

J. , Semantic role labelling for robot instructions using Echo State Networks, ESANN, 2016.