DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5 6 7 8 9...49
Hits 81 – 100 of 973

81
A Convolutional Neural Network Based Approach to Recognize Bangla Spoken Digits from Speech Signal ...
Sen, Ovishake; Al-Mahmud; Roy, Pias. - : arXiv, 2021
BASE
Show details
82
Thought Flow Nets: From Single Predictions to Trains of Model Thought ...
BASE
Show details
83
Comparing Approaches to Dravidian Language Identification ...
BASE
Show details
84
Challenges in Detoxifying Language Models ...
BASE
Show details
85
Speaking clearly improves speech segmentation by statistical learning under optimal listening conditions
In: Laboratory Phonology: Journal of the Association for Laboratory Phonology; Vol 12, No 1 (2021); 14 ; 1868-6354 (2021)
BASE
Show details
86
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
87
Translating the Unseen? Yoruba-English MT in Low-Resource, Morphologically-Unmarked Settings ...
BASE
Show details
88
MEDCOD: A Medically-Accurate, Emotive, Diverse, and Controllable Dialog System ...
BASE
Show details
89
Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales ...
BASE
Show details
90
Contextual Sentence Classification: Detecting Sustainability Initiatives in Company Reports ...
BASE
Show details
91
Tripartitions of the first person space (Tamil speakers, Condition 1) ...
Maldonado, Mora. - : Open Science Framework, 2021
BASE
Show details
92
Compositional Processing Emerges in Neural Networks Solving Math Problems ...
Abstract: A longstanding question in cognitive science concerns the learning mechanisms underlying compositionality in human cognition. Humans can infer the structured relationships (e.g., grammatical rules) implicit in their sensory observations (e.g., auditory speech), and use this knowledge to guide the composition of simpler meanings into complex wholes. Recent progress in artificial neural networks has shown that when large models are trained on enough linguistic data, grammatical structure emerges in their representations. We extend this work to the domain of mathematical reasoning, where it is possible to formulate precise hypotheses about how meanings (e.g., the quantities corresponding to numerals) should be composed according to structured rules (e.g., order of operations). Our work shows that neural networks are not only able to infer something about the structured relationships implicit in their training data, but can also deploy this knowledge to guide the composition of individual meanings into composite ... : 7 pages, 2 figures, Accepted to CogSci 2021 for poster presentation ...
Keyword: Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
URL: https://arxiv.org/abs/2105.08961
https://dx.doi.org/10.48550/arxiv.2105.08961
BASE
Hide details
93
Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning ...
BASE
Show details
94
An empirical analysis of phrase-based and neural machine translation ...
Ghader, Hamidreza. - : arXiv, 2021
BASE
Show details
95
ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning ...
BASE
Show details
96
Updater-Extractor Architecture for Inductive World State Representations ...
Moskvichev, Arseny; Liu, James A.. - : arXiv, 2021
BASE
Show details
97
Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions? ...
BASE
Show details
98
multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning ...
BASE
Show details
99
Word-level Human Interpretable Scoring Mechanism for Novel Text Detection Using Tsetlin Machines ...
BASE
Show details
100
Exceeding the Limits of Visual-Linguistic Multi-Task Learning ...
BASE
Show details

Page: 1 2 3 4 5 6 7 8 9...49

Catalogues
11
0
13
0
0
0
1
Bibliographies
49
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
923
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern