Extending a CRF-based Named Entity Recognition Model for Turkish Well Formed Text and User Generated Content

Tracking #: 1474-2686

Gökhan Şeker
Gülşen Eryiğit

Responsible editor: 
Guest Editors Social Semantics 2016

Submission type: 
Full Paper
Named entity recognition (NER), which provides useful information for many high level NLP applications and semantic web technologies, is a well-studied topic for most of the languages and especially for English. However, the modelling of morphologically rich languages (MRLs) for the NER task is still an open research area. The studies for Turkish which is a strong representative of MRLs have fallen behind the well-studied languages for a long while. In recent years, Turkish NER intrigued researchers due to its scarce data resources and the unavailability of high-performing systems. Especially, the need to semantically enrich the textual data coming with user generated content initiated many studies in this field. This article presents a CRF-based NER system which successfully models the morphologically very rich nature of this language, its extensions to expand the covered named entity types, and also to process extra challenging user generated content coming with Web 2.0. The article introduces the re-annotation of the available datasets and a brand new dataset from Web 2.0. The introduced approach reveals an exact match F1 score of 92% on a dataset collected from Turkish news articles and ~65% on different datasets collected from Web 2.0. The proposed model is believed to be easily applied to similar MRLs with relevant resources.
Full PDF Version: 


Solicited Reviews:
Click to Expand/Collapse
Review #1
By Giuseppe Rizzo submitted on 08/Nov/2016
Review Comment:

The authors have answered to my original remarks:
1) novelty, now it is clearly stated as NER on Turkish (MRL language) adapting a conventional linguistic pipeline with dedicated preprocessing, and lexical and morphological feature representation for the CRF. The improvement is indeed small, but it is an optimization of existing SOTA approaches with a clear claim and value proposition
2) minor rewording of paragraphs and resolved typesetting issues

I suggest to accept it.