Noisy Uyghur Text Normalization

no code implementations • WS 2017 • Osman Tursun, Ruket Cakici

Uyghur is the second largest and most actively used social media language in China.

Decoder

Initial Explorations of CCG Supertagging for Universal Dependency Parsing

no code implementations • CONLL 2017 • Burak Kerim Akkus, Heval Azizoglu, Ruket Cakici

In this paper we describe the system by METU team for universal dependency parsing of multilingual text.

CCG Supertagging Dependency Parsing +1

Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures

no code implementations • 15 Jan 2016 • Raffaella Bernardi, Ruket Cakici, Desmond Elliott, Aykut Erdem, Erkut Erdem, Nazli Ikizler-Cinbis, Frank Keller, Adrian Muscat, Barbara Plank

Automatic description generation from natural images is a challenging problem that has recently received a large amount of interest from the computer vision and natural language processing communities.

Retrieval

A Distributed Representation Based Query Expansion Approach for Image Captioning

no code implementations • IJCNLP 2015 • Semih Yagcioglu, Erkut Erdem, Aykut Erdem, Ruket Cakici

Image Captioning

Categorization of Turkish News Documents with Morphological Analysis

no code implementations • ACL 2013 • Burak Kerim Akku{\c{s}}, Ruket Cakici

Information Retrieval Language Identification +3

Morpheme Segmentation in the METU-Sabanc\i Turkish Treebank

no code implementations • WS 2012 • Ruket Cakici

Part-Of-Speech Tagging