1 |
Measuring the Reading-Attention Relationship: Functional Differences in Working Memory Activity During Single Word Decoding in Children With and Without Reading Disorder
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Reading in the Developing Brain ... : From Preliteracy to Fluent Reading ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
MORPHOLOGICAL AND IDENTITY PRIMING IN WORD LEARNING AND TEXT READING AS A WINDOW INTO THE MENTAL LEXICON
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Lessons learnt developing and deploying grading mechanisms for EiPE code-reading questions in CS1 classes
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Exploration of secondary EFL teachers' and students' perceptions of extensive reading in English and its implementation in Chinese secondary schools: a longitudinal case study
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Percurso desenvolvimental da leitura : o impacto de um programa de intervenção em consciência fonológica - PICF
|
|
|
|
BASE
|
|
Show details
|
|
7 |
The Componential Model of Reading: A Comprehensive Examination of Word Reading in Syrian Refugee Children
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Motivating the unmotivated: A self-study about engaging adolescent readers to read for joy before and during a pandemic
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Neural-based Knowledge Transfer in Natural Language Processing
|
|
|
|
Abstract:
In Natural Language Processing (NLP), neural-based knowledge transfer, which is to transfer out-of-domain (OOD) knowledge to task-specific neural networks, has been applied to many NLP tasks. To further explore neural-based knowledge transfer in NLP, in this dissertation, we consider both structured OOD knowledge and unstructured OOD knowledge, and deal with several representative NLP tasks. For structured OOD knowledge, we study the neural-based knowledge transfer in Machine Reading Comprehension (MRC). In single-passage MRC tasks, to bridge the gap between MRC models and human beings, which is mainly reflected in the hunger for data and the robustness to noise, we integrate the neural networks of MRC models with the general knowledge of human beings embodied in knowledge bases. On the one hand, we propose a data enrichment method, which uses WordNet to extract inter-word semantic connections as general knowledge from each given passage-question pair. On the other hand, we propose a novel MRC model named Knowledge Aided Reader (KAR), which explicitly uses the above extracted general knowledge to assist its attention mechanisms. According to the experimental results, KAR is comparable in performance with the state-of-the-art MRC models, and significantly more robust to noise than them. On top of that, when only a subset (20%-80%) of the training examples are available, KAR outperforms the state-of-the-art MRC models by a large margin, and is still reasonably robust to noise. In multi-hop MRC tasks, to probe the strength of Graph Neural Networks (GNNs), we propose a novel multi-hop MRC model named Graph Aided Reader (GAR), which uses GNN methods to perform multi-hop reasoning, but is free of any pre-trained language model and completely end-to-end. For graph construction, GAR utilizes the topic-referencing relations between passages and the entity-sharing relations between sentences, which is aimed at obtaining the most sensible reasoning clues. For message passing, GAR simulates a top-down reasoning and a bottom-up reasoning, which is aimed at making the best use of the above obtained reasoning clues. According to the experimental results, GAR even outperforms several competitors relying on pre-trained language models and filter-reader pipelines, which implies that GAR benefits a lot from its GNN methods. On this basis, GAR can further benefit from applying pre-trained language models, but pre-trained language models can mainly facilitate the within-passage reasoning rather than cross-passage reasoning of GAR. Moreover, compared with the competitors constructed as filter-reader pipelines, GAR is not only easier to train, but also more applicable to the low-resource cases. For unstructured OOD knowledge, we study the neural-based knowledge transfer in Natural Language Understanding (NLU), and focus on the neural-based knowledge transfer between languages, which is also known as Cross-Lingual Transfer Learning (CLTL). To facilitate the CLTL of NLU models, especially the CLTL between distant languages, we propose a novel CLTL model named Translation Aided Language Learner (TALL), where CLTL is integrated with Machine Translation (MT). Specifically, we adopt a pre-trained multilingual language model as our baseline model, and construct TALL by appending a decoder to it. On this basis, we directly fine-tune the baseline model as an NLU model to conduct CLTL, but put TALL through an MT-oriented pre-training before its NLU-oriented fine-tuning. To make use of unannotated data, we implement the recently proposed Unsupervised Machine Translation (UMT) technique in the MT-oriented pre-training of TALL. According to the experimental results, the application of UMT enables TALL to consistently achieve better CLTL performance than the baseline model without using more annotated data, and the performance gain is relatively prominent in the case of distant languages.
|
|
Keyword:
Cross-lingual transfer learning; Graph neural network; Information technology; Knowledge base; Knowledge graph; Knowledge transfer; Machine Reading Comprehension; Multi-hop reasoning; Natural Language Processing; Natural language understanding; Neural network; unsupervised machine translation
|
|
URL: http://hdl.handle.net/10315/39096
|
|
BASE
|
|
Hide details
|
|
11 |
Effects of multilinguistic word study instruction on word reading and spelling in the first grade: increasing metalinguistic knowledge as an instructional goal
|
|
|
|
BASE
|
|
Show details
|
|
12 |
An examination of reading, reading development and disorder in a highly transparent orthography: the case of Turkish
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Book choice : a descriptive multiple case study exploring the motivations and practices of secondary English teachers.
|
|
|
|
BASE
|
|
Show details
|
|
14 |
English machine reading comprehension: new approaches to answering multiple-choice questions
|
|
Dzendzik, Daria. - : Dublin City University. School of Computing, 2021. : Dublin City University. ADAPT, 2021
|
|
In: Dzendzik, Daria (2021) English machine reading comprehension: new approaches to answering multiple-choice questions. PhD thesis, Dublin City University. (2021)
|
|
BASE
|
|
Show details
|
|
15 |
Creole-French co-literacy as a factor of academic success in Reunion ; La Co-alphabétisation créole-français comme facteur de réussite scolaire à la Réunion
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-03597708 ; Linguistique. Université de la Réunion, 2021. Français. ⟨NNT : 2021LARE0035⟩ (2021)
|
|
BASE
|
|
Show details
|
|
16 |
繪本閱讀教學研究──以國小一年級為對象 ; The Research of Picture Books Teaching Activity : 1st Graders of a Bilingual Flementary School Students as Research Subject
|
|
|
|
BASE
|
|
Show details
|
|
17 |
南臺灣大專生的英文閱讀使用策略、程度及所屬學院關聯性之研究 ; The Relationships Among University Students' Reading Strategies, Proficiency, and Disciplines in Southern Taiwan
|
|
|
|
BASE
|
|
Show details
|
|
18 |
晨間閱讀的實施對國小二年級學生識字量學習成效之研究 ; The Effect of Morning Reading on the Literacy Level of Second-Grade Elementary School Students
|
|
|
|
BASE
|
|
Show details
|
|
19 |
大學生對於英語畢業門檻之焦慮與準備策略 ; University Students’ Test Anxiety and Preparatory Strategies for Meeting English Graduation Requirements
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Mehrsprachigkeit an der Schwelle zum Beruf. Die Funktion sprachlicher Fähigkeiten für Berufsqualifizierung und Berufseinmündung von Jugendlichen mit und ohne Migrationshintergrund (MEZ-2)
|
|
|
|
In: Hamburg : Universität 2021, 28 S. - (MEZ Arbeitspapiere; 10) (2021)
|
|
BASE
|
|
Show details
|
|
|
|