User:Gang Chen/GSoC 2013 Application: "Sliding Window PoS Tagger"

Name

Name: Gang Chen

Contact Information

Email: pkuchengang@gmail.com

IRC: Gang

GitHub Repo: https://github.com/elephantgcc

Why is it you are interested in machine translation?

I am majored in Natural Language Processing, and after taking a course on Machine Translation, I became intrested in it. It sits in the center of many NLP techniques, and has a very promising application in real life.

2 years ago, I started to intern in a statistical machine translation team of an Internet company. Since then, I began to be in deeper touch with the classic IBM models, the n-gram language models, various decoding algorithms, and many excellent open source toolkits. I was greatly attracted by the ideas and applications of machine translation. Reading the papers and making the toolkits to work properly brought me so much fun, that I still remember the sleepless night thinking about the nerual network language model.

A language is such a complicated system, that translating a sentence from one language to another has always been a challenging task. On the other hand, with the translation need drastically growing, developing better machine translation systems can also benifit the society.

Why is it that you are interested in the Apertium project?

I came across the Apertium project a year ago, when I knew about last year's GSoC. The rule-based methodology of it attracted me most. The language system is organized in a structural way in its nature, so studying the underlying rules of it should be the most direct effort to unveil the mysteries of the system. Linguistic knoledge plays a central role in language processing problems, whether it's by emprical statistics or rational analysis. So I think it is important to play with the "colorless green ideas" within a language.

Besides that, Apertium is an open source project, so ordinary people can join in and try ideas to improve it for more and better machine translation services. And what's also important is that they can be used by people all around the world.

Which of the published tasks are you interested in? What do you plan to do?

I have a great interest in the project "Sliding-window part-of-speech tagger". Currently the PoS tagger for Apertium is a HMM tagger, while the project aims to the implementation of a sliding-window PoS tagger, for better quality and efficiency.

My plans are basiclly as follows:

1) read the paper and get a full understanding to the algorithm, and familiarize myself with the Apertium pipeline. 2) implement a supervised training version of the algorithm. Implement a FST without a minimization. 3) implenent an unsupervised training version of the algorithm. Implement a FST with a minimization. 4) integrate FORBID rules into the implementation. 5) optionally, re-study the algorithm to explore further possible improvements mentioned in the paper.

Proposal Title

Application for the Apertium Project "Sliding-window part-of-speech tagger" for GSoC 2013.

Why Google and Apertium should sponsor it? How and who it will benefit in society?

The PoS tagger plays an important role in the Apertium translation pipeline. A sliding-window PoS tagger can improve the quality and efficiency of tagging, than the current HMM tagger. So its implementation will benifit both the Apertium developers and users.

I would be really thankful if Google and Apertium would sponsor this project. I think I have the knowledge and skills to accomplish the task, plus the enthusiasm for machine translation. And Apertium is a very nice community that I would like to stay with for long time.

Work plan

The task of this project is to implement a new PoS tagger. The outline of the developing procedure are mentioned above as basic plans. The detailed work plan is as follows:

Community bonding period: Get further contact with the community, and familiarize with myself with Apertium platform and the project.

Week 01: Learn about code and file formats for the tagger. Learn from and run the current HMM tagger to get a baseline.

Week 02: Implement the supervised training algorithm. Get training corpus ready for experiments.

Week 03: Learn about finite-state transducers. Implement a FST to use the new tagger.

Week 04: Continue implementation. Make tests, check for bugs, and documentation.

Deliverable #1: Finish a supervised training algorithm, with FST usable. The tagger has good a quality and efficiency.

Week 05: Re-read the paper and documentation. Write a first version of the unsupervised algorithm.

Week 06: Continue with the unsupervised algorithm. Survey techniques on how to minimize FST.

Week 07: Implement the FST minimization.

Week 08: Continue implementation. Make tests, check for bugs, and documentation.

Deliverable #2: Finish a unsupervised training algorithm, with FST minimization. The tagger has a good quality and efficiency.

Week 09: Study different ways to incorperate FORBID rules. Implement the FORBID restrictions.

Week 10: Continue implementation. Make tests, check for bugs, and documentation.

Deliverable #3: Finish an XML-based format for writing FORBID rules.

Week 11: Study further possible improvements.

Week 12: Check the code and documentation.

Deliverable #Final: A full implementation of the Sliding-window PoS tagger in Apertium.