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 ...
BASE
Show details
93
Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning ...
Abstract: Imagine you are in a supermarket. You have two bananas in your basket and want to buy four apples. How many fruits do you have in total? This seemingly straightforward question can be challenging for data-driven language models, even if trained at scale. However, we would expect such generic language models to possess some mathematical abilities in addition to typical linguistic competence. Towards this goal, we investigate if a commonly used language model, BERT, possesses such mathematical abilities and, if so, to what degree. For that, we fine-tune BERT on a popular dataset for word math problems, AQuA-RAT, and conduct several tests to understand learned representations better. Since we teach models trained on natural language to do formal mathematics, we hypothesize that such models would benefit from training on semi-formal steps that explain how math results are derived. To better accommodate such training, we also propose new pretext tasks for learning mathematical rules. We call them (Neighbor) ... : The paper has been accepted to the ACL-IJCNLP 2021 conference ...
Keyword: Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences; I.2.7; Machine Learning cs.LG
URL: https://arxiv.org/abs/2106.03921
https://dx.doi.org/10.48550/arxiv.2106.03921
BASE
Hide 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