@inproceedings{f87853ea92cf430b91f382d5c2c6f64a,
title = "Named entity recognition on real data: A preliminary investigation for Turkish",
abstract = "Named Entity Recognition (NER) is a well-studied area in natural language processing (NLP) and the reported results in the literature are generally very high (∼>%95) for most of the languages. Today, the focus area of most practical natural language applications (i.e. web mining, sentiment analysis, machine translation) is real natural language data such as Web2.0 or speech data. Nevertheless, the NER task is rarely investigated on this type of data which differs severely from formal written text. In this paper, we present 3 new Turkish data sets from different domains (on this focused area; namely from Twitter, a Speech-to-Text Interface and a Hardware Forum) annotated specifically for NER and report our first results on them. We believe, the paper draws light to the difficulty of these new domains for NER and the possible future work.",
keywords = "Conditional Random Fields, ENAMEX, Named Entity Recognition, Speech Data, Turkish, Twitter",
author = "Gokhan Celikkaya and Dilara Torunoglu and Gulsen Eryigit",
year = "2013",
doi = "10.1109/ICAICT.2013.6722801",
language = "English",
isbn = "9781467364201",
series = "AICT 2013 - 7th International Conference on Application of Information and Communication Technologies, Conference Proceedings",
publisher = "IEEE Computer Society",
booktitle = "AICT 2013 - 7th International Conference on Application of Information and Communication Technologies, Conference Proceedings",
address = "United States",
note = "7th International Conference on Application of Information and Communication Technologies, AICT 2013 ; Conference date: 23-10-2013 Through 25-10-2013",
}