SANE 2.0: System for fine grained named entity typing on textual data

Abstract

Assignment of fine-grained types to named entities is gaining popularity as one of the major Information Extraction tasks due to its applications in several areas of Natural Language Processing. Existing systems use huge knowledge bases to improve the accuracy of the fine-grained types. We designed and developed SANE 2.0, which is an extended version of our earlier work SANE (Lal et al., 2017). It uses Wikipedia categories to fine grain the type of the named entities recognized in the textual data. The entities for which types could not be found using Wikipedia categories are typed using an intelligent information extraction method that uses search results of yahoo search engine. SANE uses an efficient algorithm to assign the fine-grained type to the entities extracted from the data. Wikipedia categorizes related topics under common headings. From these categories, we constructed a database that contains Wikipedia articles and their corresponding categories. SANE uses this database to predict the category types of named entities. We use Stanford NER to identify named entities with their coarse-grained types. For locations, we use Geonames data separately. We calculate the similarity between an entity and its categories using word2vec. Each entity is assigned to the category that has the highest similarity score with it. Finally, we map the category to the most appropriate WordNet (Miller et al., 1995) type. The main contribution of this work is building a named entity typing system without the use of knowledge bases. Through our experiments, 1) we establish the usefulness of Wikipedia categories to Named Entity Typing, 2) we present an intelligent method of using yahoo search results for Named Entity Typing and 3) we show that SANE’s performance is on par with the state-of-the-art.