A Hybrid Approach for Event Extraction and Event Actor Identification

Proceedings of Recent Advances in Natural Language Processing, pages 592–597, Hissar, Bulgaria, 12-14 September 2011. A Hybrid Approach for Event Extraction and Event Actor Identification Anup Kumar Kolya1 Asif Ekbal2 Sivaji Bandyopadhyay1 1 Computer Science and Engineering Department, Jadavpur University, India 2 Patna (IITP), India anup.kolya@gmail.com, asif.ekbal@gmail.com, sivaji_cse_ju@yahoo.com Abstract This paper, we propose an approach for event extrac- tion and corresponding event actor identification- within the TimeML framework. Firstly, for event ex- traction, we develop SVM based hybrid approach and for event actor identification the baseline model is developed based on the subject information of the dependency-parsed event sentences. Then we develop an unsupervised syntax based model that is based on the relationship of the event verbs with their argument structure extracted from the head information of the chunks in the parsed sentences. Evaluation on a col- lection of TempEval-2 corpus shows the precision, recall and F-measure values for the baseline model as 64.31%, 67.74% and 65.98%, respectively and the syntax based model as 69.12%, 66.90% and 67.99%, respectively. 1 Introduction New sources of textual information, rich in events, grow significantly, such as social net- works, blogs, and wikis. They are added to old sources like the informative web sites, emails and forums, which shows the importance to manage these data automatically. One of the im- portant tasks of text analysis clearly requires identifying events described in a text and locat- ing these in time. Event extraction has emerged to be very important in improving complex nat- ural language processing (NLP) applications such as automatic summarization (Daniel et al., 2003) and question answering (QA). TimeML (Pustejovsky et al., 2003) presented a rich speci- fication for annotating events in NL text extend- ing the features of the previous one. This paper is focused on the TimeML view of events. TimeML defines events as situations that happen or occur, or elements describing states or circumstances in which something ob- tains or holds the truth. These events are gener- ally expressed by tensed or un-tensed verbs, nominalizations, adjectives, predicative clauses or prepositional phrases. The 2007 TempEval challenge attempted to address this question (Boguraev et al, 2005). In 2010, TempEval-2, event extraction task was introduced as task B. Let us consider a sentence like, BAGHDAD, Iraq (AP) _ an American leader of a U.N. weapons inspection team resumed work in Iraq Friday, nearly two months after his team was effectively blocked. Sentence 1 has three events, namely ‘re- sumed’, ‘work’ and ‘blocked’. In this sentence resumed and blocked can be considered as verbal events but work is an nonverbal event. Generally, verbal or non-verbal event are executed by some abstract entities, directly or indirectly. Entities are basically person, organization or location. 2 Event Extraction Below we present our hybrid approach for event extraction. The system is based on a supervised machine learner, Support Vector Machine (SVM). It makes use of the various features ex- tracted from the TimeML corpus. In order to im- prove the performance of the system, we incor- porate the knowledge …

Content truncated to 500 words