Named Entity Recognition on Twitter for Turkish using Semi-supervised Learning with Word Embeddings

TL;DR

This paper presents a semi-supervised neural network approach for Turkish Named Entity Recognition on Twitter data, utilizing word embeddings and language-independent features, achieving improved performance over previous systems.

Contribution

It introduces a novel semi-supervised learning method with word embeddings for Turkish NER on informal microblog texts, adaptable to other morphologically rich languages.

Findings

Achieved higher F-score than previous Turkish NER systems on Twitter

Utilized unsupervised word embeddings combined with language-independent features

Method is adaptable to other morphologically rich languages

Abstract

Recently, due to the increasing popularity of social media, the necessity for extracting information from informal text types, such as microblog texts, has gained significant attention. In this study, we focused on the Named Entity Recognition (NER) problem on informal text types for Turkish. We utilized a semi-supervised learning approach based on neural networks. We applied a fast unsupervised method for learning continuous representations of words in vector space. We made use of these obtained word embeddings, together with language independent features that are engineered to work better on informal text types, for generating a Turkish NER system on microblog texts. We evaluated our Turkish NER system on Twitter messages and achieved better F-score performances than the published results of previously proposed NER systems on Turkish tweets. Since we did not employ any language dependent features, we believe that our method can be easily adapted to microblog texts in other morphologically rich languages.