| 演題番号 | 1D1-3 |
|---|---|
| 題目 | CGMからの自己教師あり学習と条件付確率場を用いた人間行動マイニング |
| 著者 | Nguyen MinhThe(電気通信大学大学院情報システム学研究科) 川村 隆浩(電気通信大学大学院情報システム学研究科) 中川 博之(電気通信大学大学院情報システム学研究科) 田原 康之(電気通信大学大学院情報システム学研究科) 大須賀 昭彦(電気通信大学大学院情報システム学研究科) |
| 時間 | 06月09日(Wed) 09:40〜10:00 |
| 概要 | In our definition, human activity can be expressed by five basic attributes: actor, action, object, time and location. The goal of this paper is to describe a method to automatically extract all of the basic attributes and the relationships (transition and cause) between activities derived from sentences in Japanese CGM (consumer generated media). Previous work had some limitations, such as high setup cost, inability of extracting all attributes, limitation on the types of sentences that can be handled, and insufficient consideration of interdependency among attributes. To resolve these problems, this paper proposes a novel approach that uses conditional random fields and self-supervised learning. This approach treats the activity extraction as a sequence labeling problem, and has advantages such as domain-independence, scalability, and unnecessary hand-tagged data. Since it is unnecessary to fix the positions and the number of the attributes in activity sentences, this approach can extract all attributes and relationships between activities by making only a single pass over its corpus. Additionally, by converting to simpler sentences, the approach can deal with complex sentences retrieved from Japanese CGM. In an experiment, this approach achieves high precision (activity: 88.84%, attributes: over 90%, relationships: over 84%). |
| 論文 | PDFファイル |