Neural machine translation
Abstract/Contents
- Abstract
- Being able to communicate seamlessly across the entire repertoire of human languages is, to me, an ultimately rewarding goal for an intelligent system. Despite great progress in the field of Statistical Machine Translation (SMT) over the past two decades, the translation quality has not yet been satisfactory; at the same time, SMT systems become increasing complex with many different components built separately, rendering it extremely difficult to make further advancement. Recently, Neural Machine Translation (NMT) emerges as a promising solution to the problem of machine translation. At its core, NMT consists of a single deep neural network with millions of neurons that learn to directly map source sentences to target sentences. NMT is powerful because it is an end-to-end deep-learning framework that is significantly better than SMT in capturing long-range dependencies in sentences and generalizing well to unseen texts. This dissertation presents all of the essence of Neural Machine Translation (NMT), through which I discuss how I have pushed the limits of NMT, making it applicable to a wide variety of languages with state-of-the-art performance. My contributions include addressing the rare word problem with copy mechanisms, improving the attention mechanism to better select local contexts in the source sentence, and translating at the character level with a hybrid architecture. Towards the future of NMT, I discuss how to utilize data from a wide variety of tasks such as parsing, image caption generation, and unsupervised learning to improve translation; as well as how to compress NMT models for mobile devices. I conclude with how my work influences subsequent research as well as provide an in-depth coverage on the existing research landscape, highlight potential research directions, and speculate on future elements needed to further advance NMT.
Description
| Type of resource | text |
|---|---|
| Form | electronic; electronic resource; remote |
| Extent | 1 online resource. |
| Publication date | 2016 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Associated with | Luong, Minh-Thang |
|---|---|
| Associated with | Stanford University, Department of Computer Science. |
| Primary advisor | Manning, Christopher D |
| Thesis advisor | Manning, Christopher D |
| Thesis advisor | Jurafsky, Dan, 1962- |
| Thesis advisor | Le, Quoc V |
| Thesis advisor | Ng, Andrew Y, 1976- |
| Advisor | Jurafsky, Dan, 1962- |
| Advisor | Le, Quoc V |
| Advisor | Ng, Andrew Y, 1976- |
Subjects
| Genre | Theses |
|---|
Bibliographic information
| Statement of responsibility | Minh-Thang Luong. |
|---|---|
| Note | Submitted to the Department of Computer Science. |
| Thesis | Thesis (Ph.D.)--Stanford University, 2016. |
| Location | electronic resource |
Access conditions
- Copyright
- © 2016 by Thang Minh Luong
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...