Scientific publications

Фамхынг Д.К.

Частичное обучение в логико-марковской сети в задаче извлечения временной информации из текста

// Электронные библиотеки: перспективные методы и технологии, электронные коллекции: Труды XI Всероссийской научной конференции RCDL'2009. Петрозаводск: КарНЦ РАН, 2009. C. 259-263

Hung Pham D.Q. Semi-supervised learning with Markov Logic Networks and application to temporal information processing // Digital Libraries: Advanced Methods and Technologies, Digital Collections: Proceedings of the XI All-Russian Research Conference RCDL'2009. Petrozavodsk: KRC RAS, 2009. Pp. 259-263

This paper addressed the problem of temporal information extraction from text. We proposed a solution using Markov Logic Networks. The knowledge is presented in first-order logic production rules. We used both hard clauses and clauses that associated with weights to indicate their confidence. A new co-training algorithm was proposed that take benefit of unlabeled data to boost accuracy of Markov logic networks.

Semi-supervised learning with Markov Logic Networks and application to temporal information processing (270 Kb, total downloads: 179)

Last modified: October 16, 2009