2014) “Experiments to Improve Named Entity Recognition on Turkish Tweets

Social media texts are significant informa-tion sources for several application areas including trend analysis, event monitor-ing, and opinion mining. Unfortunately, existing solutions for tasks such as named entity recognition that perform well on formal texts usually perform poorly when applied to social media texts. In this pa-per, we report on experiments that have the purpose of improving named entity recog-nition on Turkish tweets, using two dif-ferent annotated data sets. In these ex-periments, starting with a baseline named entity recognition system, we adapt its recognition rules and resources to better fit Twitter language by relaxing its capital-ization constraint and by diacritics-based expansion of its lexical resources, and we employ a simplistic normalization scheme on tweets to observe the effects of these on the overall named entity recognition per-formance on Turkish tweets. The evalua-tion results of the system with these differ-ent settings are provided with discussions of these results.