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

Named Entity Recognition on Twitter for Turkish using Semi-supervised Learning with Word Embeddings Eda Okur*†, Hakan Demir†, Arzucan ¨Ozg¨ur† *Intel Corporation Istanbul, Turkey eda.okur@intel.com †Department of Computer Engineering, Bo˘gazic¸i University Istanbul, Turkey {hakan.demir, arzucan.ozgur}@boun.edu.tr 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. Keywords: Named Entity Recognition, Turkish NER, Twitter 1. Introduction Microblogging environments, which allow users to post short messages, have gained increased popularity in the last decade. Twitter, which is one of the most popular mi- croblogging platforms, has become an interesting platform for exchanging ideas, following recent developments and trends, or discussing any possible topic. Since Twitter has an enormously wide range of users with varying interests and sharing preferences, a significant amount of content is being created rapidly. Therefore, mining such platforms can extract valuable information. As a consequence, ex- tracting information from Twitter has become a hot topic of research. For Twitter text mining, one popular research area is opinion mining or sentiment analysis, which is surely useful for companies or political parties to gather infor- mation about their services and products (K¨okciyan et al., 2013). Another popular research area is content analysis, or more specifically topic modeling, which is useful for text classification and filtering applications on Twitter (Hong and Davison, 2010). Moreover, event monitoring and trend analysis are also other examples of useful application areas on microblog texts (Kireyev et al., 2009). In order to build successful social media analysis appli- cations, it is necessary to employ successful processing tools for Natural Language Processing (NLP) tasks such as Named Entity Recognition (NER). NER is a critical stage for various NLP applications including machine transla- tion, question answering and opinion mining. The aim of NER is to classify and locate atomic elements in a given text into predefined categories like the names of the per- sons, locations, and organizations (PLOs). NER on well-written texts is accepted as a solved prob- lem for well-studied languages like English. However, it still needs further work for morphologically rich languages like Turkish due to their complex structure and relatively scarce language processing tools and data sets (S¸eker and Eryi˘git, 2012). In addition, most …

Content truncated to 500 words