Segmenting Hashtags using Automatically Created Training Data

no code implementations • LREC 2016 • Arda {\c{C}}elebi, Arzucan {\"O}zg{\"u}r

Our approach is unsupervised in the sense that instead of using manually segmented hashtags for training the machine learning classifiers, we automatically create our training data by using tweets as well as by automatically extracting hashtag segmentations from a large corpus.

BIG-bench Machine Learning

Self-training a Constituency Parser using n-gram Trees

no code implementations • LREC 2014 • Arda {\c{C}}elebi, Arzucan {\"O}zg{\"u}r

In this study, we tackle the problem of self-training a feature-rich discriminative constituency parser.

Constituency Parsing Sentence

BOUNCE: Sentiment Classification in Twitter using Rich Feature Sets

no code implementations • SEMEVAL 2013 • Nadin K{\"o}kciyan, Arda {\c{C}}elebi, Arzucan {\"O}zg{\"u}r, Suzan {\"U}sk{\"u}darl{\i}

Classification General Classification +2

Semi-Supervised Discriminative Language Modeling with Out-of-Domain Text Data

no code implementations • NAACL 2013 • Arda {\c{C}}elebi, Murat Sara{\c{c}}lar

Language Modelling Speech Recognition