Kernels for structured natural language data

Jun Suzuki, Yutaka Sasaki, Eisaku Maeda

研究成果: Conference contribution

4 被引用数 (Scopus)


This paper devises a novel kernel function for structured natural language data. In the field of Natural Language Processing, feature extraction consists of the following two steps: (1) syntactically and semantically analyzing raw data, i.e., character strings, then representing the results as discrete structures, such as parse trees and dependency graphs with part-of-speech tags; (2) creating (possibly high-dimensional) numerical feature vectors from the discrete structures. The new kernels, called Hierarchical Directed Acyclic Graph (HDAG) kernels, directly accept DAGs whose nodes can contain DAGs. HDAG data structures are needed to fully reflect the syntactic and semantic structures that natural language data inherently have. In this paper, we define the kernel function and show how it permits efficient calculation. Experiments demonstrate that the proposed kernels are superior to existing kernel functions, e.g., sequence kernels, tree kernels, and bag-of-words kernels.

ホスト出版物のタイトルAdvances in Neural Information Processing Systems 16 - Proceedings of the 2003 Conference, NIPS 2003
出版社Neural information processing systems foundation
ISBN(印刷版)0262201526, 9780262201520
出版ステータスPublished - 2004
イベント17th Annual Conference on Neural Information Processing Systems, NIPS 2003 - Vancouver, BC, Canada
継続期間: 2003 12 82003 12 13


名前Advances in Neural Information Processing Systems


Other17th Annual Conference on Neural Information Processing Systems, NIPS 2003
CityVancouver, BC

ASJC Scopus subject areas

  • コンピュータ ネットワークおよび通信
  • 情報システム
  • 信号処理


「Kernels for structured natural language data」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。