Named Entity Recognition Experiments on Turkish Texts

Küçük, Dilek; Yazıcı, Adnan

doi:10.1007/978-3-642-04957-6_45

Cited by 40 publications

(35 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These datasets are also used by Küçük and Yazıcı for the rule-based recognition system [11,12,13]. Contents of the datasets are given in Table 4.1.…”

Section: Chapter 4 4 Evaluation and Discussionmentioning

confidence: 99%

“…Our secondary target is using this learning based system with previously designed rule-based NER system in [12,13]. Joint utilization of these systems would create a hybrid system which is expected to work better than both of rule-based system and learning based system.…”

Section: Contributions and Motivationmentioning

confidence: 99%

“…In rule-based recognition, one of the most widely known NER systems for Turkish is the study of Küçük and Yazıcı presented in [11,12,13]. They used lexical resources and patterns for extracting named entities.…”

Section: Named Entity Recognition In Turkishmentioning

confidence: 99%

“…Proposed hybrid system is based on employment of Bayesian learning system together with the rule based system presented in [12,13,14]. Three different datasets will be referred in following sections:…”

Section: Hybrid Systemmentioning

confidence: 99%

See 3 more Smart Citations

Named Entity Recognition in Turkish with Bayesian Learning and Hybrid Approaches

Yavuz

Küçük

Yazıcı

2013

Information Sciences and Systems 2013

Self Cite

View full text Add to dashboard Cite

iii I hereby declare that all information in this document has been obtained and presented in accordance with academic rules and ethical conduct. I also declare that, as required by these rules and conduct, I have fully cited and referenced all material and results that are not original to this work. The final goal of structured information extraction is to populate a database and reach data effectively. Our study focuses on named entity recognition (NER) which is an important subtask of IE. NER is the task that deals with extraction of named entities like person, location, organization names, temporal expressions (date and time) and numerical expressions (money and percent). NER research on Turkish is known to be rare. There are rule-based, learning based and hybrid systems for NER on Turkish texts. Some of the learning approaches used for NER in Turkish are conditional random fields (CRF), rote learning, rule extraction and generalization.In this thesis, we propose a learning based named entity recognizer for Turkish texts which employs a modified version of Bayesian learning as the learning scheme. To the best of our knowledge, this is the first learning based system that uses Bayesian

show abstract

“…These datasets are also used by Küçük and Yazıcı for the rule-based recognition system [11,12,13]. Contents of the datasets are given in Table 4.1.…”

Section: Chapter 4 4 Evaluation and Discussionmentioning

confidence: 99%

Section: Contributions and Motivationmentioning

confidence: 99%

Section: Named Entity Recognition In Turkishmentioning

confidence: 99%

Section: Hybrid Systemmentioning

confidence: 99%

See 2 more Smart Citations

Named Entity Recognition in Turkish with Bayesian Learning and Hybrid Approaches

Yavuz

Küçük

Yazıcı

2013

Information Sciences and Systems 2013

Self Cite

View full text Add to dashboard Cite

show abstract

“…A clustering-based approach for NER on microtexts is presented in (Jung, 2012), a lightweight filter based approach for NER on tweets is described in (de Oliveira et al, 2013), and a series of NER experiments on targeted tweets in Polish is presented in (Piskorski and Ehrmann, 2013). Finally, an adaptation of the ANNIE component of GATE framework to microblog texts, called TwitIE, is described in (Bontcheva et al, 2013).Considering NER research on Turkish texts, various approaches have been employed so far including those based on using Hidden Markov Models (HMM) (Tür et al, 2003), on manually engineered recognition rules (Küçük and Yazıcı, 2009;Küçük and Yazıcı, 2012), on rule learning (Tatar and Ç icekli, 2011), and on CRFs (Yeniterzi, 2011;. All of these approaches have been proposed for news texts and the CRF-based approach is reported to outperform the previous proposals with a balanced F-Measure of about 91%.…”

mentioning

confidence: 99%

Proceedings of the 5th Workshop on Language Analysis for Social Media (LASM)

Farzindar¹,

Inkpen²,

Gamon³

et al. 2014

View full text Add to dashboard Cite

Over the past few years, online social networking sites (Facebook, Twitter, Youtube, Flickr, MySpace, LinkedIn, Metacafe, Vimeo, etc.) have revolutionized the way we communicate with individuals, groups and communities, and altered everyday practices. The unprecedented volume and variety of usergenerated content as well as the user interaction network constitute new opportunities for understanding social behavior and building socially-intelligent systems.This 5th workshop attracted several submissions from around the world. Each paper was assigned to four reviewers. For the final workshop program, and for inclusion in these proceedings, nine regular papers were selected. The workshop program features two keynote presentations: one by Kalina Bontcheva, Senior Researcher in the Natural Language Processing Group, Department of Computer Science, University of Sheffield, and one on Industrial perspectives presented by NLP Technologies, Montreal Canada, on social media monitoring and innovative tools.One of the goals of LASM 2014 was to reflect a wide range of different research efforts and results of language analysis with implications for fields such as natural language processing, computational linguistics, sociolinguistics and psycholinguistics. We invited original and unpublished research papers on all topics related to the analysis of language on social media, including the following topics:• What are people talking about on social media?• How are they expressing themselves?• Why do they scribe?• Natural language processing techniques for social media analysis• How do language and social network properties interact?• Semantic Web / Ontologies / Domain models to aid in social data understanding • Characterizing Participants via Linguistic Analysis• Language, Social Media and Human Behavior This workshop would not have been possible without the hard work of many people. We would like to thank all Program Committee members and external reviewers for their effort in providing high-quality reviews in a timely manner. We thank all the authors who submitted their papers, as well as the authors whose papers were selected, for their help with preparing the final copy. We are in debt to the EACL 2014 Workshop co-Chairs. We would also like to thank our industry partners for their support and for making LASM 2014 a successful workshop; NLP Technologies, Microsoft Research and IBM Almaden. AbstractUser-generated content has become a recurrent resource for NLP tools and applications, hence many efforts have been made lately in order to handle the noise present in short social media texts. The use of normalisation techniques has been proven useful for identifying and replacing lexical variants on some of the most informal genres such as microblogs. But annotated data is needed in order to train and evaluate these systems, which usually involves a costly process. Until now, most of these approaches have been focused on English and they were not taking into account demographic variables such as the user location and gender. ...

show abstract

High-Precision Person Name Extraction from Turkish Texts Using Wikipedia

Küçük

2015

Natural Language Processing and Information Systems

View full text Add to dashboard Cite

Named Entity Recognition Experiments on Turkish Texts

Cited by 40 publications

References 12 publications

Named Entity Recognition in Turkish with Bayesian Learning and Hybrid Approaches

Named Entity Recognition in Turkish with Bayesian Learning and Hybrid Approaches

Proceedings of the 5th Workshop on Language Analysis for Social Media (LASM)

High-Precision Person Name Extraction from Turkish Texts Using Wikipedia

Contact Info

Product

Resources

About