• Publications
  • Influence
Earthquake shakes Twitter users: real-time event detection by social sensors
This paper investigates the real-time interaction of events such as earthquakes in Twitter and proposes an algorithm to monitor tweets and to detect a target event and produces a probabilistic spatiotemporal model for the target event that can find the center and the trajectory of the event location. Expand
Measuring semantic similarity between words using web search engines
A robust semantic similarity measure that uses the information available on the Web to measure similarity between words or entities and a novel approach to compute semantic similarity using automatically extracted lexico-syntactic patterns from text snippets is proposed. Expand
Keyword extraction from a single document using word co-occurrence statistical information
A new keyword extraction algorithm that applies to a single document without using a corpus and shows comparable performance to tfidf without using an corpus is presented. Expand
Joint Multimodal Learning with Deep Generative Models
The proposed joint multimodal variational autoencoder (JMVAE), in which all modalities are independently conditioned on joint representation, models a joint distribution of modalities and can generate and reconstruct them more properly than conventional VAEs. Expand
Tweet Analysis for Real-Time Event Detection and Earthquake Reporting System Development
An earthquake reporting system for use in Japan is developed and an algorithm to monitor tweets and to detect a target event is proposed, which produces a probabilistic spatiotemporal model for the target event that can find the center of the event location. Expand
A Web Search Engine-Based Approach to Measure Semantic Similarity between Words
This work proposes an empirical method to estimate semantic similarity using page counts and text snippets retrieved from a web search engine for two words, and proposes a novel pattern extraction algorithm and a pattern clustering algorithm that significantly improves the accuracy in a community mining task. Expand
POLYPHONET: An advanced social network extraction system from the Web
A social network extraction system called POLYPHONET is proposed, which employs several advanced techniques to extract relations of persons, to detect groups of people, and to obtain keywords for a person. Expand
Automatic Discovery of Personal Name Aliases from the Web
The proposed method to extract aliases of a given personal name from the web outperforms numerous baselines and previously proposed name alias extraction methods, achieving a statistically significant mean reciprocal rank (MRR) of 0.67. Expand
Generative Adversarial Nets from a Density Ratio Estimation Perspective
Generative adversarial networks (GANs) are successful deep generative models. GANs are based on a two-player minimax game. However, the objective function derived in the original motivation isExpand
Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection
Okutama-Action, a new video dataset for aerial view concurrent human action detection, consists of 43 minute-long fully-annotated sequences with 12 action classes, and features many challenges missing in current datasets. Expand