Kunihiko Sadamasa


2019

pdf
Cross-Sentence N-ary Relation Extraction using Lower-Arity Universal Schemas
Kosuke Akimoto | Takuya Hiraoka | Kunihiko Sadamasa | Mathias Niepert
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Most existing relation extraction approaches exclusively target binary relations, and n-ary relation extraction is relatively unexplored. Current state-of-the-art n-ary relation extraction method is based on a supervised learning approach and, therefore, may suffer from the lack of sufficient relation labels. In this paper, we propose a novel approach to cross-sentence n-ary relation extraction based on universal schemas. To alleviate the sparsity problem and to leverage inherent decomposability of n-ary relations, we propose to learn relation representations of lower-arity facts that result from decomposing higher-arity facts. The proposed method computes a score of a new n-ary fact by aggregating scores of its decomposed lower-arity facts. We conduct experiments with datasets for ternary relation extraction and empirically show that our method improves the n-ary relation extraction performance compared to previous methods.

2015

pdf
Cross-lingual Text Classification Using Topic-Dependent Word Probabilities
Daniel Andrade | Kunihiko Sadamasa | Akihiro Tamura | Masaaki Tsuchida
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies