Taiichi Hashimoto

Efficient Sentence Retrieval Based on Syntactic Structure

This paper proposes an efficient method of sentence retrieval based on syntactic structure. Collins proposed Tree Kernel to calculate structural similarity. However, structual retrieval based on Tree Kernel is not practicable because the size of the index table by Tree Kernel becomes impractical. We propose more efficient algorithms approximating Tree Kernel: Tree Overlapping and Subpath Set. These algorithms are more efficient than Tree Kernel because indexing is possible with practical computation resources. The results of the experiments comparing these three algorithms showed that structural retrieval with Tree Overlapping and Subpath Set were faster than that with Tree Kernel by 100 times and 1,000 times respectively.

The patent mining task in the seventh NTCIR workshop

This paper introduces the Patent Mining Task of the Seventh NTCIR Workshop and the test collections produced in this task. The tasks goal was the classification of research papers written in either Japanese or English in terms of the International Patent Classification (IPC) system, which is a global standard. For this task, 12 participant groups submitted 49 runs. In this paper, we also report the evaluation results of the task.

Research history generation from metainformation of research papers using maximum margin clustering

Recently, analysing research papers to understand research trends researchers research topics automatically from metainformation of research papers published on the internet. Our method is based on Maximum Margin Clustering (MMC). We describe how to represent research papers in form of vectors using metainformation about them and how to initialise the hyperplane for MMC automatically. In the experiments, we show that the purity of our method is higher than that achieved in previous work based on k-Means (0.58 vs 0.35) and entropy of our method is lower than that of previous work (0.415 vs 0.47). Experiment results also illustrates that keyword information of research papers affects the most to clustering result.

Research history generation using maximum margin clustering of research papers based on metainformation

Our research aim is the automatic generation of a researchers research history from research articles published on the internet. Research history generation based on the k-Means clustering algorithm has been proposed in previous work. However, the performance of the k-Means algorithm is unsatisfactory. We propose a method based on Maximum Margin Clustering (MMC). MMC is a new clustering algorithm based on Support Vector Machines (SVM). It is known that MMC is better than existing clustering algorithms such as k-Means. In this paper, we describe how to convert articles into vectors using metainformation about them and how to decide an initial setting for MMC automatically. We demonstrate by experiment that the purity of a method based on MMC is about 0.58 and its entropy is about 0.415. This result is better than that achieved in previous work (purity: 0.35, entropy: 0.47).