1 |
Cross-Situational Learning Towards Robot Grounding
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03628290 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
2 |
Cross-Situational Learning Towards Robot Grounding
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03628290 ; 2022 (2022)
|
|
Abstract:
How do children acquire language through unsupervised or noisy supervision? How do their brain process language? We take this perspective to machine learning and robotics, where part of the problem is understanding how language models can perform grounded language acquisition through noisy supervision and discussing how they can account for brain learning dynamics. Most prior works have tracked the co-occurrence between single words and referents to model how infants learn wordreferent mappings. This paper studies cross-situational learning (CSL) with full sentences: we want to understand brain mechanisms that enable children to learn mappings between words and their meanings from full sentences in early language learning. We investigate the CSL task on a few training examples with two sequence-based models: (i) Echo State Networks (ESN) and (ii) Long-Short Term Memory Networks (LSTM). Most importantly, we explore several word representations including One-Hot, GloVe, pretrained BERT, and fine-tuned BERT representations (last layer token representations) to perform the CSL task. We apply our approach to three diverse datasets (two grounded language datasets and a robotic dataset) and observe that (1) One-Hot, GloVe, and pretrained BERT representations are less efficient when compared to representations obtained from fine-tuned BERT. (2) ESN online with final learning (FL) yields superior performance over ESN online continual learning (CL), offline learning, and LSTMs, indicating the more biological plausibility of ESNs and the cognitive process of sentence reading. (2) LSTM with fewer hidden units showcases higher performance for small datasets, but LSTM with more hidden units is Cross-Situational Learning needed to perform reasonably well on larger corpora. (4) ESNs demonstrate better generalization than LSTM models for increasingly large vocabularies. Overall, these models are able to learn from scratch to link complex relations between words and their corresponding meaning concepts, handling polysemous and synonymous words. Moreover, we argue that such models can extend to help current human-robot interaction studies on language grounding and better understand children's developmental language acquisition. We make the code publicly available * .
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]; [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO]; [SDV.NEU]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]; BERT; cross-situational learning; echo state networks; grounded language; LSTM
|
|
URL: https://hal.archives-ouvertes.fr/hal-03628290/document https://hal.archives-ouvertes.fr/hal-03628290/file/Journal_of_Social_and_Robotics.pdf https://hal.archives-ouvertes.fr/hal-03628290
|
|
BASE
|
|
Hide details
|
|
3 |
Teach Your Robot Your Language! Trainable Neural Parser for Modelling Human Sentence Processing: Examples for 15 Languages
|
|
|
|
In: ISSN: 2379-8920 ; EISSN: 2379-8939 ; IEEE Transactions on Cognitive and Developmental Systems ; https://hal.inria.fr/hal-01964541 ; IEEE Transactions on Cognitive and Developmental Systems, Institute of Electrical and Electronics Engineers, Inc, 2019, ⟨10.1109/TCDS.2019.2957006⟩ ; https://doi.org/10.1109/tcds.2019.2957006 (2019)
|
|
BASE
|
|
Show details
|
|
4 |
Syntactic Reanalysis in Language Models for Speech Recognition
|
|
|
|
In: 2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) ; https://hal.inria.fr/hal-01558462 ; 2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), Sep 2017, Lisbon, Portugal ; http://icdl-epirob.org/ (2017)
|
|
BASE
|
|
Show details
|
|
5 |
Teach Your Robot Your Language! Trainable Neural Parser for Modelling Human Sentence Processing: Examples for 15 Languages
|
|
|
|
In: https://hal.inria.fr/hal-01665807 ; 2017 (2017)
|
|
BASE
|
|
Show details
|
|
6 |
Recurrent Neural Network for Syntax Learning with Flexible Predicates for Robotic Architectures
|
|
|
|
In: The Sixth Joint IEEE International Conference Developmental Learning and Epigenetic Robotics (ICDL-EPIROB) ; https://hal.inria.fr/hal-01417697 ; The Sixth Joint IEEE International Conference Developmental Learning and Epigenetic Robotics (ICDL-EPIROB), Sep 2016, Cergy, France ; http://icdl-epirob.org/ (2016)
|
|
BASE
|
|
Show details
|
|
7 |
Recurrent Neural Network Sentence Parser for Multiple Languages with Flexible Meaning Representations for Home Scenarios
|
|
|
|
In: IROS Workshop on Bio-inspired Social Robot Learning in Home Scenarios ; https://hal.inria.fr/hal-01417667 ; IROS Workshop on Bio-inspired Social Robot Learning in Home Scenarios, Oct 2016, Daejon, South Korea ; https://www.informatik.uni-hamburg.de/wtm/SocialRobotsWorkshop2016/index.php (2016)
|
|
BASE
|
|
Show details
|
|
8 |
Semantic Role Labelling for Robot Instructions using Echo State Networks
|
|
|
|
In: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) ; https://hal.inria.fr/hal-01417701 ; European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), Apr 2016, Bruges, Belgium ; https://www.elen.ucl.ac.be/esann/index.php?pg=esann16_programme (2016)
|
|
BASE
|
|
Show details
|
|
9 |
Using Natural Language Feedback in a Neuro-inspired Integrated Multimodal Robotic Architecture
|
|
|
|
In: 25th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN) ; https://hal.inria.fr/hal-01417706 ; 25th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), Aug 2016, New York City, United States. pp.52 - 57, ⟨10.1109/ROMAN.2016.7745090⟩ ; http://www.tc.columbia.edu/conferences/roman2016/ (2016)
|
|
BASE
|
|
Show details
|
|
10 |
A Recurrent Neural Network for Multiple Language Acquisition: Starting with English and French
|
|
|
|
In: Proceedings of the NIPS Workshop on Cognitive Computation: Integrating Neural and Symbolic Approaches (CoCo 2015) ; https://hal.inria.fr/hal-02561258 ; Proceedings of the NIPS Workshop on Cognitive Computation: Integrating Neural and Symbolic Approaches (CoCo 2015), Dec 2015, Montreal, Canada ; http://ceur-ws.org/Vol-1583/ (2015)
|
|
BASE
|
|
Show details
|
|
|
|