| 1 |
From Biological Synapses to “Intelligent” Robots
|
|
|
|
In: ISSN: 2079-9292 ; Electronics ; https://hal.archives-ouvertes.fr/hal-03590998 ; Electronics, MDPI, 2022, 11 (5), pp.707. ⟨10.3390/electronics11050707⟩ (2022)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Cross-Situational Learning Towards Robot Grounding
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03628290 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Cross-Situational Learning Towards Robot Grounding
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03628290 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Finding the best way to put media bias research into practice via an annotation app ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Are neural language models sensitive to false belief? A computational study. ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Structured, flexible, and robust: comparing linguistic plans and explanations generated by humans and large language models ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Can distributional semantics explain performance on the false belief task? ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Learning Bidirectional Translation between Descriptions and Actions with Small Paired Data ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Unsupervised Multimodal Word Discovery based on Double Articulation Analysis with Co-occurrence cues ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Machine infelicity in a poignant visitor setting: Comparing human and AI’s ability to analyze discourse
|
|
|
|
In: Research outputs 2014 to 2021 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Integrating Blockchains and Intelligent Agents in the Pursuit of Artificial General Intelligence
|
|
|
|
In: Senior Honors Theses (2022)
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Grounding Language to Autonomously-Acquired Skills via Goal Generation
|
|
|
|
In: ICLR 2021 - Ninth International Conference on Learning Representation ; https://hal.inria.fr/hal-03121146 ; ICLR 2021 - Ninth International Conference on Learning Representation, May 2021, Vienna / Virtual, Austria (2021)
|
|
BASE
|
|
Show details
|
|
|
| 13 |
"It Is Not the Robot Who Learns, It Is Me." Treating Severe Dysgraphia Using Child-Robot Interaction
|
|
|
|
In: ISSN: 1664-0640 ; Frontiers in Psychiatry ; https://hal.sorbonne-universite.fr/hal-03152170 ; Frontiers in Psychiatry, Frontiers, 2021, 12, pp.596055. ⟨10.3389/fpsyt.2021.596055⟩ (2021)
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Hierarchical-Task Reservoir for Online Semantic Analysis from Continuous Speech
|
|
|
|
In: ISSN: 2162-237X ; IEEE Transactions on Neural Networks and Learning Systems ; https://hal.inria.fr/hal-03031413 ; IEEE Transactions on Neural Networks and Learning Systems, IEEE, 2021, ⟨10.1109/TNNLS.2021.3095140⟩ ; https://ieeexplore.ieee.org/abstract/document/9548713/metrics#metrics (2021)
|
|
Abstract:
International audience ; In this paper, we propose a novel architecture called Hierarchical-Task Reservoir (HTR) suitable for real-time applications for which different levels of abstraction are available. We apply it to semantic role labeling based on continuous speech recognition. Taking inspiration from the brain, that demonstrates hierarchies of representations from perceptive to integrative areas, we consider a hierarchy of four sub-tasks with increasing levels of abstraction (phone, word, part-of-speech and semantic role tags). These tasks are progressively learned by the layers of the HTR architecture. Interestingly, quantitative and qualitative results show that the hierarchical-task approach provides an advantage to improve the prediction. In particular, the qualitative results show that a shallow or a hierarchical reservoir, considered as baselines, do not produce estimations as good asthe HTR model would. Moreover, we show that it is possible to further improve the accuracy of the model by designing skip connections and by considering word embedding in the internal representations. Overall, the HTR outperformed the other stateof-the-art reservoir-based approaches and it resulted in extremely efficient w.r.t. typical RNNs in deep learning (e.g. LSTMs). The HTR architecture is proposed as a step toward the modeling of online and hierarchical processes at work in the brain during language comprehension.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [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]; [SCCO.LING]Cognitive science/Linguistics; [SDV.NEU]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]; Anytime Process; Hierarchical Processing; Hierarchical Reservoir Computing; Natural Language Processing; Part-of-Speech; POS tagging; Recurrent Neural Networks; Semantic Role Labelling; Speech Recognition
|
|
URL: https://hal.inria.fr/hal-03031413
https://doi.org/10.1109/TNNLS.2021.3095140
https://hal.inria.fr/hal-03031413v3/file/PedrelliHinaut2020_preprint_HAL-v3.pdf
https://hal.inria.fr/hal-03031413v3/document
|
|
BASE
|
|
Hide details
|
|
|
| 15 |
Does the Goal Matter? Emotion Recognition Tasks Can Change the Social Value of Facial Mimicry towards Artificial Agents
|
|
|
|
In: ISSN: 2296-9144 ; Frontiers in Robotics and AI ; https://hal.archives-ouvertes.fr/hal-03409678 ; Frontiers in Robotics and AI, Frontiers Media S.A., 2021, 8, ⟨10.3389/frobt.2021.699090⟩ (2021)
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Measuring Equity Mindsets and Improvisational Practices Through Language Patterns in Equity Simulations ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 18 |
Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 19 |
VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 20 |
Embodying Pre-Trained Word Embeddings Through Robot Actions ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
