41 |
Understanding the Cognitive Heterogeneity Associated with Autistic Traits: the Influence of Transdiagnostic Factors and Context ...
|
|
|
|
BASE
|
|
Show details
|
|
43 |
THE SIZE BIAS: DOES IT EXIST, AND HOW WOULD WE EXAMINE IT IN THE BRAIN ...
|
|
|
|
BASE
|
|
Show details
|
|
46 |
Meta-Analysis Data from 'A Role for Visual Memory in Vocabulary Development: A Systematic Review and Meta-Analysis' ...
|
|
|
|
BASE
|
|
Show details
|
|
47 |
Εφαρμογές βαθιάς μάθησης ... : Applications of deep learning ...
|
|
|
|
BASE
|
|
Show details
|
|
48 |
Αναγνώριση νοηματικής γλώσσας με τεχνικές βαθιάς μηχανικής μάθησης ... : Deep learning based sign language recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
49 |
The Phonological Latching Network
|
|
|
|
In: BIOLINGUISTICS; Vol. 14 (2020): Special Issue—Biolinguistic Research in the 21st Century; 102-129 ; 1450-3417 (2021)
|
|
BASE
|
|
Show details
|
|
50 |
Discriminative feature modeling for statistical speech recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
51 |
Towards Learning Terminological Concept Systems from Multilingual Natural Language Text ...
|
|
|
|
BASE
|
|
Show details
|
|
52 |
How the input shapes the acquisition of verb morphology: elicited production and computational modelling in two highly inflected languages ...
|
|
|
|
BASE
|
|
Show details
|
|
53 |
Which Theory of Language for Deep Neural Networks? Speech and Cognition in Humans and Machines ...
|
|
Capone, Luca. - : Technology and Language, 2(4), 29-60, 2021
|
|
BASE
|
|
Show details
|
|
54 |
Data-Driven Analysis of Zebra Finch Song Copying and Learning
|
|
|
|
BASE
|
|
Show details
|
|
55 |
Sentiment Analysis of Amazon Electronic Product Reviews using Deep Learning
|
|
|
|
BASE
|
|
Show details
|
|
56 |
Phonetic processing in speech sound disorder (Gerwin et al., 2021) ...
|
|
|
|
BASE
|
|
Show details
|
|
57 |
Machine Learning Methods for Automatic Silent Speech Recognition Using a Wearable Graphene Strain Gauge Sensor. ...
|
|
|
|
BASE
|
|
Show details
|
|
58 |
Phonetic processing in speech sound disorder (Gerwin et al., 2021) ...
|
|
|
|
BASE
|
|
Show details
|
|
59 |
Automated Paraphrase Quality Assessment Using Language Models and Transfer Learning
|
|
|
|
In: Computers; Volume 10; Issue 12; Pages: 166 (2021)
|
|
Abstract:
Learning to paraphrase supports both writing ability and reading comprehension, particularly for less skilled learners. As such, educational tools that integrate automated evaluations of paraphrases can be used to provide timely feedback to enhance learner paraphrasing skills more efficiently and effectively. Paraphrase identification is a popular NLP classification task that involves establishing whether two sentences share a similar meaning. Paraphrase quality assessment is a slightly more complex task, in which pairs of sentences are evaluated in-depth across multiple dimensions. In this study, we focus on four dimensions: lexical, syntactical, semantic, and overall quality. Our study introduces and evaluates various machine learning models using handcrafted features combined with Extra Trees, Siamese neural networks using BiLSTM RNNs, and pretrained BERT-based models, together with transfer learning from a larger general paraphrase corpus, to estimate the quality of paraphrases across the four dimensions. Two datasets are considered for the tasks involving paraphrase quality: ULPC (User Language Paraphrase Corpus) containing 1998 paraphrases and a smaller dataset with 115 paraphrases based on children’s inputs. The paraphrase identification dataset used for the transfer learning task is the MSRP dataset (Microsoft Research Paraphrase Corpus) containing 5801 paraphrases. On the ULPC dataset, our BERT model improves upon the previous baseline by at least 0.1 in F1-score across the four dimensions. When using fine-tuning from ULPC for the children dataset, both the BERT and Siamese neural network models improve upon their original scores by at least 0.11 F1-score. The results of these experiments suggest that transfer learning using generic paraphrase identification datasets can be successful, while at the same time obtaining comparable results in fewer epochs.
|
|
Keyword:
language models; natural language processing; paraphrase quality assessment; recurrent neural networks; transfer learning
|
|
URL: https://doi.org/10.3390/computers10120166
|
|
BASE
|
|
Hide details
|
|
60 |
Extracting Semantic Relationships in Greek Literary Texts
|
|
|
|
In: Sustainability ; Volume 13 ; Issue 16 (2021)
|
|
BASE
|
|
Show details
|
|
|
|