{"type":"ScholarlyArticle","title":"A Hybrid Neural Model for Type Classification of Entity Mentions","authors":[{"name":"Li Dong","slug":"li-dong","given":"Li","family":"Dong","affiliation":""},{"name":"Furu Wei","slug":"furu-wei","given":"Furu","family":"Wei","affiliation":""},{"name":"Hong Sun","slug":"hong-sun","given":"Hong","family":"Sun","affiliation":""},{"name":"Ming Zhou","slug":"ming-zhou-2","given":"Ming","family":"Zhou","affiliation":""},{"name":"Ke Xu","slug":"ke-xu-2","given":"Ke","family":"Xu","affiliation":""}],"abstract":"The semantic class (i.e., type) of an entity plays a vital role in many natural language processing tasks, such as question answering. However, most of existing type classification systems extensively rely on hand-crafted features. This paper introduces a hybrid neural model which classifies entity mentions to a wide-coverage set of 22 types derived from DBpedia. It consists of two parts. The mention model uses recurrent neural networks to recursively obtain the vector representation of an entity mention from the words it contains. The context model, on the other hand, employs multilayer perceptrons to obtain the hidden representation for contextual information of a mention. Representations obtained by the two parts are used together to predict the type distribution. Using automatically generated data, these two parts are jointly learned. Experimental studies illustrate that the proposed approach outperforms baseline methods. Moreover, when type information provided by our method is used in a question answering system, we observe a 14.7% relative improvement for the top-1 accuracy of answers.","doi":null,"url":"https://ijcai.org/proceedings/2015/179","pdf":"https://ijcai.org/proceedings/2015/0179.pdf","markdown":"https://ijcai.org/proceedings/2015/179.md","bibtex":"https://ijcai.org/proceedings/2015/bibtex/179","volume":{"slug":"2015","title":"Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2015","url":"https://ijcai.org/proceedings/2015/","year":2015,"location":"Buenos Aires, Argentina","dates":"25–31 July 2015","editors":"Qiang Yang and Michael Wooldridge","isbn":"978-1-57735-738-4","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Natural Language Processing","track":"Main Track","number":179,"pages":{"first":1243,"last":1248},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}