Pattern Learning for Event Extraction using Monolingual Statistical Machine Translation

Event extraction systems typically take advantage of language and domain-specific knowledge bases, including patterns that are used to identify specific facts in text; techniques to acquire these patterns can be considered one of the most challenging issues. In this work, we propose a languageindependent and weakly-supervised algorithm to automatically discover linear patterns from texts. Our approach is based on a phrase-based statistical machine translation system trained on monolingual data. A bootstrapping version of the algorithm is proposed. Our method was tested on patterns with different domain-specific semantic roles in three languages: English, Spanish and Russian. Performance shows the feasibility of our approach and its capability of working with texts in various languages.