"Parsing Web 2.0 Sentences"

Web 2.0 Cümlelerinin Ayrıştırılması


Hi! This is our Natural Language Processing project group in
Computer Engineering Department of Istanbul Technical University.

Within this web page, you may find some information about us, our research, our publications and our social events.
For further information, please don't hesitate to send an e-mail.




Parsing Web 2.0 Sentences (Web 2.0 Cümlelerinin Ayrıştırılması)

In this project, we are performing R&D activities related to all NLP stages required to perform language processing of raw Turkish text on Web 2.0 (social media data such as Twitter, Facebook etc...). These stages may be briefly listed as the following: creating a new Turkish Web 2.0 dependency treebank, presenting new annotation methods to be used in this treebank and updating the existing Turkish treebank according to these new methods, text normalization, morphological analysis and disambiguation, named entity recognition and dependency parsing. We opened a web service for our automatic annotation tools to be used online. The web service is called ITU Turkish Natural Language Processing Pipeline (ITU Türkçe Doğal Dil İşleme Yazılım Zinciri). The details of this web service are given in the following publication, please refer to it if you would use this tool in your research:

Gülşen Eryiğit. ITU Turkish NLP Web Service. In Proceedings of the Demonstrations at the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2014). Gothenburg, Sweden, April 2014. (bibtex) (pdf) (webpage)

Some packages of web service are as follows:

[ Back to top ]

Project Group

Below you may find full time, part time research assistants and volunteers of the project.


Below you may find publications of our Project.

[ Back to top ]

Social Events and Conference Photos

You may find some photos of our project assistants and conference photos that we have attended.

[ Back to top ]

©2013 Dilara Torunoğlu , Last revised November 2013