Page: 1 2 3 4 5 6 7 8 9... 71
81 |
Visual generics: How adults understand generic language with different visualizations ...
|
|
|
|
BASE
|
|
Show details
|
|
82 |
Improving Multilingual Models for the Swedish Language : Exploring CrossLingual Transferability and Stereotypical Biases
|
|
|
|
BASE
|
|
Show details
|
|
83 |
Effects of EFL Learning on L1 Chinese Lexis
|
|
|
|
In: Sustainability; Volume 13; Issue 23; Pages: 13496 (2021)
|
|
BASE
|
|
Show details
|
|
84 |
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
|
|
85 |
Transfer Capital or Transfer Deficit: A Dual Perspective of English Learning of ESL College Transfer Students
|
|
|
|
In: Sustainability; Volume 14; Issue 1; Pages: 214 (2021)
|
|
BASE
|
|
Show details
|
|
86 |
DATLMedQA: A Data Augmentation and Transfer Learning Based Solution for Medical Question Answering
|
|
|
|
In: Applied Sciences; Volume 11; Issue 23; Pages: 11251 (2021)
|
|
BASE
|
|
Show details
|
|
87 |
Modeling Heritage Language Phonetics and Phonology: Toward an Integrated Multilingual Sound System
|
|
|
|
In: Languages; Volume 6; Issue 4; Pages: 209 (2021)
|
|
BASE
|
|
Show details
|
|
88 |
NASca and NASes: Two Monolingual Pre-Trained Models for Abstractive Summarization in Catalan and Spanish
|
|
|
|
In: Applied Sciences ; Volume 11 ; Issue 21 (2021)
|
|
BASE
|
|
Show details
|
|
89 |
Heritage Tagalog Phonology and a Variationist Framework of Language Contact
|
|
|
|
In: Languages; Volume 6; Issue 4; Pages: 201 (2021)
|
|
BASE
|
|
Show details
|
|
90 |
Reusing Monolingual Pre-Trained Models by Cross-Connecting Seq2seq Models for Machine Translation
|
|
|
|
In: Applied Sciences ; Volume 11 ; Issue 18 (2021)
|
|
BASE
|
|
Show details
|
|
91 |
Generating Synthetic Disguised Faces with Cycle-Consistency Loss and an Automated Filtering Algorithm
|
|
|
|
In: Mathematics; Volume 10; Issue 1; Pages: 4 (2021)
|
|
BASE
|
|
Show details
|
|
92 |
Methods for Detoxification of Texts for the Russian Language
|
|
|
|
In: Multimodal Technologies and Interaction ; Volume 5 ; Issue 9 (2021)
|
|
BASE
|
|
Show details
|
|
93 |
Machine Translation in Low-Resource Languages by an Adversarial Neural Network
|
|
|
|
In: Applied Sciences; Volume 11; Issue 22; Pages: 10860 (2021)
|
|
BASE
|
|
Show details
|
|
94 |
3D Expression-Invariant Face Verification Based on Transfer Learning and Siamese Network for Small Sample Size
|
|
|
|
In: Electronics ; Volume 10 ; Issue 17 (2021)
|
|
BASE
|
|
Show details
|
|
95 |
Spanish-Catalan linguistic transfers: A study of lexical availability in Lleida ; Transferències lingüístiques castellà-català: un estudi de disponibilitat lèxica a Lleida
|
|
|
|
In: Treballs de Sociolingüística Catalana; Núm. 31 (2021): L’estandardologia comparada: teoria i pràctica; 149-164 (2021)
|
|
BASE
|
|
Show details
|
|
96 |
Держать, читать oder говорить доклад?! – Kollokationen und andere lexikalische Einheiten in der Sprachausbildung russischer Herkunftssprecher
|
|
|
|
BASE
|
|
Show details
|
|
97 |
Identifying Datooga loans in Iraqw - and the other way round ...
|
|
|
|
BASE
|
|
Show details
|
|
98 |
Identifying Datooga loans in Iraqw - and the other way round ...
|
|
|
|
BASE
|
|
Show details
|
|
99 |
Держать, читать oder говорить доклад?! – Kollokationen und andere lexikalische Einheiten in der Sprachausbildung russischer Herkunftssprecher ...
|
|
|
|
BASE
|
|
Show details
|
|
100 |
Surveying Motion Lexicalisation Patterns in L1-Portuguese/FL-English Bilinguals ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8 9... 71
|
|