1 |
Talking about torment : agency assignment and grammatical metaphor in pain communication ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
An experimental approach to recomplementation : evidence from monolingual and bilingual Spanish
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Noun incorporation and resultative verb compounding in Mandarin Chinese
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Teachers’ and center leaders’ sensemaking of inquiry-based professional learning in early childhood education and care programs : a multiple case study
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Marketing of Library Services for Enhanced Accessibility in National Open University of Nigeria: Challenges and Strategies for Intervention
|
|
|
|
In: Library Philosophy and Practice (e-journal) (2019)
|
|
BASE
|
|
Show details
|
|
9 |
Unsupervised learning of lexical subclasses from phonotactics
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Unsupervised learning of disentangled representations for speech with neural variational inference models
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Beliefs about grammar instruction among post-secondary second-language learners and teachers
|
|
|
|
BASE
|
|
Show details
|
|
14 |
The effects of a text structure and paraphrasing intervention on the main idea generation and reading comprehension of struggling readers in grades 4 and 5
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Literacies of surveillance : transfronterizo children translanguaging identity across borders, inspectors and surveillance
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Why belonging matters for college students’ academic engagement : antecedents and consequences of sense of classroom belonging
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Transfer learning for low-resource natural language analysis
|
|
|
|
Abstract:
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017. ; This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. ; Cataloged from student-submitted PDF version of thesis. ; Includes bibliographical references (pages 131-142). ; Expressive machine learning models such as deep neural networks are highly effective when they can be trained with large amounts of in-domain labeled training data. While such annotations may not be readily available for the target task, it is often possible to find labeled data for another related task. The goal of this thesis is to develop novel transfer learning techniques that can effectively leverage annotations in source tasks to improve performance of the target low-resource task. In particular, we focus on two transfer learning scenarios: (1) transfer across languages and (2) transfer across tasks or domains in the same language. In multilingual transfer, we tackle challenges from two perspectives. First, we show that linguistic prior knowledge can be utilized to guide syntactic parsing with little human intervention, by using a hierarchical low-rank tensor method. In both unsupervised and semi-supervised transfer scenarios, this method consistently outperforms state-of-the-art multilingual transfer parsers and the traditional tensor model across more than ten languages. Second, we study lexical-level multilingual transfer in low-resource settings. We demonstrate that only a few (e.g., ten) word translation pairs suffice for an accurate transfer for part-of-speech (POS) tagging. Averaged across six languages, our approach achieves a 37.5% improvement over the monolingual top-performing method when using a comparable amount of supervision. In the second monolingual transfer scenario, we propose an aspect-augmented adversarial network that allows aspect transfer over the same domain. We use this method to transfer across different aspects in the same pathology reports, where traditional domain adaptation approaches commonly fail. Experimental results demonstrate that our approach outperforms different baselines and model variants, yielding a 24% gain on this pathology dataset. ; by Yuan Zhang. ; Ph. D.
|
|
Keyword:
Electrical Engineering and Computer Science
|
|
URL: http://hdl.handle.net/1721.1/108847
|
|
BASE
|
|
Hide details
|
|
20 |
Multi-modal and deep learning for robust speech recognition
|
|
|
|
BASE
|
|
Show details
|
|
|
|