Hiroyuki Akama

Also published as: Hiroyuki Akam


2010

pdf bib
Network Analysis of Korean Word Associations
Jaeyoung Jung | Na Li | Hiroyuki Akama
Proceedings of the NAACL HLT 2010 First Workshop on Computational Neurolinguistics

2008

pdf bib
Random Graph Model Simulations of Semantic Networks for Associative Concept Dictionaries
Hiroyuki Akama | Jaeyoung Jung | Terry Joyce | Maki Miyake
Coling 2008: Proceedings of the 3rd Textgraphs workshop on Graph-based Algorithms for Natural Language Processing

pdf bib
How to Take Advantage of the Limitations with Markov Clustering?–The Foundations of Branching Markov Clustering (BMCL)
Hiroyuki Akama | Maki Miyake | Jaeyoung Jung
Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-II

2007

pdf bib
Hierarchical Structure in Semantic Networks of Japanese Word Associations
Maki Miyake | Terry Joyce | Jaeyoung Jung | Hiroyuki Akama
Proceedings of the 21st Pacific Asia Conference on Language, Information and Computation

2006

pdf bib
Recurrent Markov Cluster (RMCL) Algorithm for the Refinement of the Semantic Network
Jaeyoung Jung | Maki Miyake | Hiroyuki Akam
Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)

The purpose of this work is to propose a new methodology to ameliorate the Markov Cluster (MCL) Algorithm that is well known as an efficient way of graph clustering (Van Dongen, 2000). The MCL when applied to a graph of word associations has the effect of producing concept areas in which words are grouped into the similar topics or similar meanings as paradigms. However, since a word is determined to belong to only one cluster that represents a concept, Markov clusters cannot show the polysemy or semantic indetermination among the properties of natural language. Our Recurrent MCL (RMCL) allows us to create a virtual adjacency relationship among the Markov hard clusters and produce a downsized and intrinsically informative semantic network of word association data. We applied one of the RMCL algorithms (Stepping-stone type) to a Japanese associative concept dictionary and obtained a satisfactory level of performance in refining the semantic network generated from MCL.