The facets could be organized into a hierarchical taxonomy, based on relations such as is-a, member-of, etc. In this paper, we use square brackets to indicate facets (e.g. For example, particular entities may belong to different categories such as football players, movies, cities, companies, websites, etc. Facets typically are more finely granular characteristics of entities, often times used to categorize entities. What did Obama say about any or, given he likes to play basketball? Here, the term facet refers to some aspect of an entity dis- coverable from an ontology or taxonomy of entities.What are people saying about Obama and global warming?.What did Obama say about global warming?.And can be specified as combination of keywords, entities, and/or facets. politician, basketball player), or anyone. Obama), a facet (a type or category of entities, e.g. The parameter could be specified as a specific entity (e.g. The system supports search for quotes in many different ways, in the form of What did say about ? where and are specified by users. We store each extracted quotation, together with its associated properties, in an inverted index that enables efficient and flexible retrieval. We apply entity recognition to identify named entities and concepts mentioned in the quotations. news articles, blogs, etc.), including identifying the speaker and the quote, as well as the context of the quote being made. We use natural language processing techniques to extract quotations from text (i.e. We demonstrate a faceted search system for querying semantically annotated quotations, and show its advantage over the bag-of-keyword approach. ![]() We support faceted search on both speakers and entities mentioned in the quotes. We apply computational linguistic techniques such as coreference resolution, entity recognition and disambiguation to improve both precision and recall of the quote detection. ![]() In addition, each day we add around 60 thousand new quotes extracted from around 50 thousand news articles or blogs. APIs for real- time querying of over 10 million quotes extracted from recent news feeds are publicly available. this paper, we describe a system that automatically extracts quotations from news feeds, and allows efficient retrieval of the semantically annotated quotes.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |