| 1 |
Deciphering Undersegmented Ancient Scripts Using Phonetic Prior
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 9, Pp 69-81 (2021) (2021)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Typology-aware neural dependency parsing : challenges and directions
|
|
|
|
BASE
|
|
Show details
|
|
|
| 5 |
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
|
|
|
| 6 |
Hierarchical low-rank tensors for multilingual transfer parsing
|
|
|
|
In: http://aclweb.org/anthology/D/D15/D15-1213.pdf (2015)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Context-dependent type-level models for unsupervised morpho-syntactic induction
|
|
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Linguistically Motivated Models for Lightly-Supervised Dependency Parsing
|
|
|
|
In: http://people.csail.mit.edu/tahira/main.pdf (2014)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Low-rank tensors for scoring dependency structures
|
|
|
|
In: http://people.csail.mit.edu/tommi/papers/Lei-ACL14.pdf (2014)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
The MIT Faculty has made this article openly available. Please share how this access benefits you
|
|
|
|
In: http://dspace.mit.edu/openaccess-disseminate/1721.1/59314/ (2014)
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Multilingual Part-of-Speech Tagging: Two Unsupervised Approaches
|
|
|
|
In: http://dspace.mit.edu/openaccess-disseminate/1721.1/62804/ (2014)
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Linguistically motivated models for lightly-supervised dependency parsing
|
|
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Morphological segmentation : an unsupervised method and application to Keyword Spotting ; Unsupervised method and application to KWS
|
|
|
|
BASE
|
|
Show details
|
|
|
| 15 |
Learning to map into a universal pos tagset
|
|
|
|
In: http://people.csail.mit.edu/yuanzh/papers/emnlp2012.pdf (2012)
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Grounding Linguistic Analysis in Control Applications
|
|
|
|
In: http://people.csail.mit.edu/branavan/papers/branavan-thesis.pdf (2012)
|
|
BASE
|
|
Show details
|
|
|
| 18 |
In-domain relation discovery with meta-constraints via posterior regularization
|
|
|
|
In: http://people.csail.mit.edu/regina/my_papers/sem_acl2011.pdf (2011)
|
|
BASE
|
|
Show details
|
|
|
| 19 |
Learning to win by reading manuals in a monte-carlo framework
|
|
|
|
In: http://www.aclweb.org/anthology/P11-1028/ (2011)
|
|
BASE
|
|
Show details
|
|
|
| 20 |
Non-linear monte-carlo search in civilization II
|
|
|
|
In: http://people.csail.mit.edu/branavan/papers/ijcai2011.pdf (2011)
|
|
BASE
|
|
Show details
|
|
|
|
|
