M
Masaaki Nagata
Researcher at Nippon Telegraph and Telephone
Publications - 214
Citations - 3499
Masaaki Nagata is an academic researcher from Nippon Telegraph and Telephone. The author has contributed to research in topics: Machine translation & Parsing. The author has an hindex of 28, co-authored 206 publications receiving 3081 citations. Previous affiliations of Masaaki Nagata include Spacelabs Healthcare & Kyoto University.
Papers
More filters
Proceedings ArticleDOI
Neural Headline Generation on Abstract Meaning Representation
TL;DR: This paper investigates the usefulness of structural syntactic and semantic information additionally incorporated in a baseline neural attention-based model to encode results obtained from an abstract meaning representation (AMR) parser using a modified version of Tree-LSTM.
Proceedings Article
Mining Revision Log of Language Learning SNS for Automated Japanese Error Correction of Second Language Learners
TL;DR: The authors extracted a largescale Japanese learners' corpus from the revision log of a language learning SNS and used it as training data for learners' error correction using an SMT approach.
Journal ArticleDOI
Mining revision log of language learning SNS for automated Japanese error correction
TL;DR: An attempt to extract a largescale Japanese learners’ corpus from the revision log of a language learning SNS is presented, and Experimental results show that the character-wise model outperforms the word-wise models.
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 ArticleDOI
A stochastic Japanese morphological analyzer using a forward-DP backward- A* N-best search algorithm
TL;DR: A novel method for segmenting the input sentence into words and assigning parts of speech to the words and an efficient two-pass N-best search algorithm is presented, suitable for written Japanese.