Y
Yasuhisa Yoshida
Researcher at Nippon Telegraph and Telephone
Publications - 11
Citations - 331
Yasuhisa Yoshida is an academic researcher from Nippon Telegraph and Telephone. The author has contributed to research in topics: Tree (data structure) & Automatic summarization. The author has an hindex of 6, co-authored 11 publications receiving 293 citations. Previous affiliations of Yasuhisa Yoshida include Nara Institute of Science and Technology.
Papers
More filters
Proceedings Article
Single-Document Summarization as a Tree Knapsack Problem
TL;DR: This paper proposes a single document summarization method based on the trimming of a discourse tree that improves ROUGE scores and formulate the problem of trimming a dependency-based discourse tree as a Tree Knapsack Problem, then solve it with integer linear programming (ILP).
Proceedings Article
Transfer learning for multiple-domain sentiment analysis — identifying domain dependent/independent word polarity
TL;DR: A novel Bayesian probabilistic model is proposed to handle multiple source and multiple target domains and can tell whether each word's polarity is domain-dependent or domain-independent, and construct a word polarity dictionary for each domain.
Proceedings ArticleDOI
Dependency-based Discourse Parser for Single-Document Summarization
TL;DR: The evaluation results showed that the TKP with the novel discourse parser outperformed that with the state-of-the-art RST-DT parser, and achieved almost equivalent ROUGE scores to the T kp with the gold DEP-DT.
Journal ArticleDOI
Summarization based on task-oriented discourse parsing
TL;DR: A new single document summarization system that enables us to combine discourse parsing and summarization in a unified scheme by training a discourse parser specially for summarization by using summaries.
Journal ArticleDOI
Summarizing a document by trimming the discourse tree
TL;DR: This paper formulated the summarization procedure as a Tree Knapsack Problem whose tree corresponds to the DEP-DT, and proposed a method that exploits a discourse tree structure to produce coherent summaries.