| 1 |
Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?
|
|
|
|
In: Seventh Workshop on Noisy User-generated Text (W-NUT 2021, colocated with EMNLP 2021) ; https://hal.inria.fr/hal-03527328 ; Seventh Workshop on Noisy User-generated Text (W-NUT 2021, colocated with EMNLP 2021), Jan 2022, punta cana, Dominican Republic ; https://aclanthology.org/2021.wnut-1.47/ (2022)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Cross-lingual few-shot hate speech and offensive language detection using meta learning
|
|
|
|
In: ISSN: 2169-3536 ; EISSN: 2169-3536 ; IEEE Access ; https://hal.archives-ouvertes.fr/hal-03559484 ; IEEE Access, IEEE, 2022, 10, pp.14880-14896. ⟨10.1109/ACCESS.2022.3147588⟩ (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 |
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
|
|
|
| 5 |
Ensemble of Opinion Dynamics Models to Understand the Role of the Undecided in the Vaccination Debate ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 6 |
The Online Behaviour of the Algerian Abusers in Social Media Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Chess AI: Competing Paradigms for Machine Intelligence
|
|
|
|
In: Entropy; Volume 24; Issue 4; Pages: 550 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Discussion Networks and Resilience of College Students: Explicating Tie Strength in Communicative Interaction
|
|
|
|
In: International Journal of Communication; Vol 16 (2022); 25 ; 1932-8036 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
“Thou Shalt Not Take the Lord’s Name in Vain”: A Methodological Proposal to Identify Religious Hate Content on Digital Social Networks
|
|
|
|
In: International Journal of Communication; Vol 16 (2022); 22 ; 1932-8036 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Singing voice separation using waveform-level deep neural networks ... : Διαχωρισμός Φωνητικών χρησιμοποιώντας Βαθιά Νευρωνικά Δίκτυα σε Επίπεδο Κυματομορφών ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Καταστολή ηχητικού θορύβου μέσω τεχνικών μηχανικής μάθησης ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Conceptual structure and the growth of scientific knowledge ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 13 |
INNOVATIVE APPROACHES AND METHODS IN TEACHING FOREIGN LANGUAGES ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 14 |
EMAKG: an enriched version of the Microsoft Academic Knowledge Graph ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 15 |
INNOVATIVE APPROACHES AND METHODS IN TEACHING FOREIGN LANGUAGES ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 16 |
EMAKG: an enriched version of the Microsoft Academic Knowledge Graph ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Multilingual Abusiveness Identification on Code-Mixed Social Media Text ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 18 |
MuMiN: A Large-Scale Multilingual Multimodal Fact-Checked Misinformation Social Network Dataset ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 20 |
Discovering Affinity Relationships between Personality Types ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
