1 |
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 https://hal.archives-ouvertes.fr/hal-03628290v2/file/Journal_of_Social_and_Robotics.pdf https://hal.archives-ouvertes.fr/hal-03628290v2/document
|
|
BASE
|
|
Hide details
|
|
2 |
Cross-Situational Learning Towards Robot Grounding
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03628290 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
3 |
A Neural Pairwise Ranking Model for Readability Assessment ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
pNLP-Mixer: an Efficient all-MLP Architecture for Language ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Does Corpus Quality Really Matter for Low-Resource Languages? ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
A New Generation of Perspective API: Efficient Multilingual Character-level Transformers ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Learning Bidirectional Translation between Descriptions and Actions with Small Paired Data ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Improving Intrinsic Exploration with Language Abstractions ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Chain-based Discriminative Autoencoders for Speech Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Cross-Platform Difference in Facebook and Text Messages Language Use: Illustrated by Depression Diagnosis ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Improving Word Translation via Two-Stage Contrastive Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reduction ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
EnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in English ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Adversarial Robustness of Neural-Statistical Features in Detection of Generative Transformers ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
The Mapping of Deep Language Models on Brain Responses Primarily Depends on their Performance
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03361439 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
19 |
Recognizing lexical units in low-resource language contexts with supervised and unsupervised neural networks
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03429051 ; [Research Report] LACITO (UMR 7107). 2021 (2021)
|
|
BASE
|
|
Show details
|
|
20 |
Privacy and utility of x-vector based speaker anonymization
|
|
|
|
In: https://hal.inria.fr/hal-03197376 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
|
|