Difference between revisions of "User:Gor ar"

From Apertium
Jump to navigation Jump to search
(Add to category)
(Move the proposal to a subpage)
 
Line 1: Line 1:
[[User:Gor_ar/proposal_2017|My proposal for GSoC 2017]]
GSoC 2017 Proposal: UD and Apertium Integration.

== Contact information ==

'''Name:''' Gor Arakelyan
'''Email:''' gor19973010@gmail.com

'''Skype:''' gor.arakelyan4

== About me ==

I am a second-year student in YSU (Yerevan State University) at the department of Informatics and Applied Mathematics.

I am interested in natural language processing, especially for low resource languages, like my native language Armenian. Apertium seems to be a perfect platform for that.

== Background ==
The most important problem for Armenian NLP (and possibly for many others) is the lack of a properly annotated treebank. In order to help linguists to quickly annotate large amounts of text, an annotation tool with easy to use interface is required. I believe UD annotatrix is a very good tool to start with.

== Proposed solution ==
Currently it lacks convenient UI to [https://github.com/jonorthwash/ud-annotatrix/issues/6 edit POS tags] or [https://github.com/jonorthwash/ud-annotatrix/issues/3 dependency relations]. I propose the following solutions:

* The simple textbox in UD annotatrix can be replaced by a more convenient rich code editor (like [https://codemirror.net CodeMirror])
* Rich editor will provide autocompletion for UD specific tags (VERB, ADV, NOUN, Definite etc.)
* In the later stages we can make autocomplete more intelligent:
* - e.g. display only verb specific tags when POS is set to verb (tense)
* - use previously annotated data to provide suggestions
* Make UD annotatrix portable so it can be included in larger applications, e.g. in an app that uses a backend to save annotations
* Support [https://github.com/jonorthwash/ud-annotatrix/issues/8 multiword tokens] in the visualisation

== My experience ==
I have been doing web development for 3 years now. Recently I worked on [https://github.com/YerevaNN/armtreebank an open source tool for corpus management] (currently used for Armenian only). It involved coding in HTML, JS and Python.

[[Category:GSoC 2017 Student Proposals]]

Latest revision as of 15:29, 31 March 2017