Detecting Hypernym/Hyponym in Science and Technology Thesaurus Using Entropy-Based Clustering of Word Vectors

@article{Kawamura2017DetectingHI,
  title={Detecting Hypernym/Hyponym in Science and Technology Thesaurus Using Entropy-Based Clustering of Word Vectors},
  author={Takahiro Kawamura and Motoki Sekine and Katsuji Matsumura},
  journal={Int. J. Semantic Computing},
  year={2017},
  volume={11},
  pages={433-450}
}
Thesauri for science and technology information are increasingly used in bibliometrics and scientometrics. However, the manual construction and maintenance of thesauri are costly and time consuming; thus, methods for semi-automatic construction and maintenance are being actively studied. We propose a method that expands an existing thesaurus with specified terms extracted from the abstracts of articles. Specifically, we assign the terms to certain subcategories by our novel clustering method… CONTINUE READING

Results and Topics from this paper.

Key Quantitative Results

  • In experiments, the terms were correctly classified into the Japan Science and Technology thesaurus with 83.3% precision and 71.4% recall.