TAILIEUCHUNG - Báo cáo khoa học: "Composite Kernels For Relation Extraction"

The automatic extraction of relations between entities expressed in natural language text is an important problem for IR and text understanding. In this paper we show how different kernels for parse trees can be combined to improve the relation extraction quality. On a public benchmark dataset the combination of a kernel for phrase grammar parse trees and for dependency parse trees outperforms all known tree kernel approaches alone suggesting that both types of trees contain complementary information for relation extraction. . | Composite Kernels For Relation Extraction Hannes Korte Fraunhofer IAIS St. Augustin Germany Gerhard Paass Fraunhofer IAIS St. Augustin Germany Frank Reichartz Fraunhofer IAIS St. Augustin Germany @ Abstract The automatic extraction of relations between entities expressed in natural language text is an important problem for IR and text understanding. In this paper we show how different kernels for parse trees can be combined to improve the relation extraction quality. On a public benchmark dataset the combination of a kernel for phrase grammar parse trees and for dependency parse trees outperforms all known tree kernel approaches alone suggesting that both types of trees contain complementary information for relation extraction. 1 Introduction The same semantic relation between entities in natural text can be expressed in many ways . Obama was educated at Harvard Obama is a graduate of Harvard Law School or Obama went to Harvard College . Relation extraction aims at identifying such semantic relations in an automatic fashion. As a preprocessing step named entity taggers detect persons locations schools etc. mentioned in the text. These techniques have reached a sufficient performance level on many datasets Tjong et al. 2003 . In the next step relations between recognized entities . person-educated-in-school Obama Harvard are identified. Parse trees provide extensive information on syntactic structure. While feature-based methods may compare only a limited number of structural details kernel-based methods may explore an often exponential number of characteristics of trees without explicitly representing the features. Zelenko et al. 2003 and Culotta and Sorensen 2004 proposed kernels for dependency trees DTs inspired by string kernels. Zhang et al. 2006 suggested a kernel for phrase grammar parse trees. Bunescu and Mooney 2005 investigated a kernel that computes similarities between nodes on the .

TAILIEUCHUNG - Chia sẻ tài liệu không giới hạn
Địa chỉ : 444 Hoang Hoa Tham, Hanoi, Viet Nam
Website : tailieuchung.com
Email : tailieuchung20@gmail.com
Tailieuchung.com là thư viện tài liệu trực tuyến, nơi chia sẽ trao đổi hàng triệu tài liệu như luận văn đồ án, sách, giáo trình, đề thi.
Chúng tôi không chịu trách nhiệm liên quan đến các vấn đề bản quyền nội dung tài liệu được thành viên tự nguyện đăng tải lên, nếu phát hiện thấy tài liệu xấu hoặc tài liệu có bản quyền xin hãy email cho chúng tôi.
Đã phát hiện trình chặn quảng cáo AdBlock
Trang web này phụ thuộc vào doanh thu từ số lần hiển thị quảng cáo để tồn tại. Vui lòng tắt trình chặn quảng cáo của bạn hoặc tạm dừng tính năng chặn quảng cáo cho trang web này.