Targetable Named Entity Recognition in Social Media
This addresses the need for adaptable NER systems in domains with frequently updated entities, such as social media, though it is incremental as it focuses on a single entity type.
The paper tackles the problem of recognizing targetable named entities like movie titles in social media without retraining for new entities, achieving F1-scores of 76.19% and 78.70% on evaluation sets to show unbiased performance.
We present a novel approach for recognizing what we call targetable named entities; that is, named entities in a targeted set (e.g, movies, books, TV shows). Unlike many other NER systems that need to retrain their statistical models as new entities arrive, our approach does not require such retraining, which makes it more adaptable for types of entities that are frequently updated. For this preliminary study, we focus on one entity type, movie title, using data collected from Twitter. Our system is tested on two evaluation sets, one including only entities corresponding to movies in our training set, and the other excluding any of those entities. Our final model shows F1-scores of 76.19% and 78.70% on these evaluation sets, which gives strong evidence that our approach is completely unbiased to any par- ticular set of entities found during training.