Event Information Extraction System (EIEE): FSM vs HMM

Authors: Shaukat Wasi, Zubair A. Shaikh, Sajid Qasmi, Hussain Sachwani, Rehman Lalani, Aamir Chagani

Abstract:

Automatic Extraction of Event information from social text stream (emails, social network sites, blogs etc) is a vital requirement for many applications like Event Planning and Management systems and security applications. The key information components needed from Event related text are Event title, location, participants, date and time. Emails have very unique distinctions over other social text streams from the perspective of layout and format and conversation style and are the most commonly used communication channel for broadcasting and planning events. Therefore we have chosen emails as our dataset. In our work, we have employed two statistical NLP methods, named as Finite State Machines (FSM) and Hidden Markov Model (HMM) for the extraction of event related contextual information. An application has been developed providing a comparison among the two methods over the event extraction task. It comprises of two modules, one for each method, and works for both bulk as well as direct user input. The results are evaluated using Precision, Recall and F-Score. Experiments show that both methods produce high performance and accuracy, however HMM was good enough over Title extraction and FSM proved to be better for Venue, Date, and time.

Keywords: Emails, Event Extraction, Event Detection, Finite state machines, Hidden Markov Model.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1331045

References:

[1] J. Allan, et al., "Topic Detection and Tracking Pilot Study Final Report," in DARPA Broadcast News Transcription and Understanding Workshop, 1998.
[2] J. Allan, R. Papka, and V. Lavrenko, "On-Line New Event Detection and Tracking," presented at SIGIR'98, Melbourne, Australia, 1998.
[3] Y. Yang, T. Pierce, and J. Carbonell, "A Study on Retrospective and Online Event Detection," presented at SIGIR'98, Melbourne, Australia, 1998.
[4] Y. Yang, et al., "Learning Approaches for Detecting and Tracking News Events," IEEE Intelligent Systems Special Issue on Applications of Intelligent Information Retrieval, vol. 4, pp. 32-43, 1999.
[5] G. Kumaran and J. Allan, "Text Classification and Named Entities for New Event Detection," presented at SIGIR'04, Sheffield, South Yorkshire, UK, 2004.
[6] D. Kusui, K. Tateishi, and T. fukushima, "Information Extraction and Visualization Fro Internet Documents," NEC Journal of Advanced Technology, vol. 2, 2005.
[7] K. Chen, L. Luesukprasert, and S. T. Chou, "Hot Topic Extraction Based on Timeline Analysis and Multidimensional Sentence Modeling," IEEE Transactions on Knowledge and Data Engineering, vol. 19, 2007.
[8] Z. Kuo, L. J. Zi, and W. Gang, "New Event Detection Based on Indexing-Tree and Named Entity," presented at SIGIR'07, Amsterdam, The Netherlands, 2007.
[9] X. Wan, E. Milios, and N. Kalyaniwalla, "Link-Based Event Detection in Email Communication Networks," presented at SAC'09, Honolulu, Hawaii, U.S.A, 2009.
[10] Q. Zhao and P. Mitra, "Event Detection and Visualization for Social Text Streams," presented at ICWSM, Coloroda, USA, 2007.
[11] Q. Zhao, P. Mitra, and B. Chen, "Temporal and Information Flow Based Event Detection from Social Text Streams," presented at American Association for Artificial Intelligence (AAAI 2007), Vancouver, British Columbia, Canada 2007.
[12] V. Pekar, "Information Extraction from Email Announcements," in Lncs, Natural Language Processing and Information Systems. Berlin Heidelberg: Springer Verlag, 2005, pp. 372-375.
[13] C. X. Lin, et al., "Pet: A Statistical Model for Popular Events Tracking in Social Communities," presented at SIGKDD, New York, USA, 2010.
[14] V. Ha-Thuc, et al., "Event Intensity Tracking in Weblog Collections," presented at ICWSM-DCW' 09, California, USA, 2009.
[15] H. Sayyadi, M. Hurst, and A. Maykov, "Event Detection and Tracking in Social Streams," presented at Association for Advancement of Artificial Intelligence (AAAI'09), 2009.
[16] H. Becker, M. Naaman, and L. Gravano, "Event Identfication in Social Media," presented at Twelfth International Workshop on the Web Databases (WebDB 2009), Providence, USA, 2009.
[17] H. Becker, M. Naaman, and L. Gravano, "Learning Similarity Metrics for Event Identification in Social Media," presented at WSDM, New York, USA, 2010.
[18] P. King and S. H. Mayeng, "Usefulness of Temporal Information Automatically Extracted from News Articles for Topic Tracking," ACM Transactions on Asian Language Information Processing, vol. 3, pp. 227-242, 2004.
[19] J. HOBBS, et al., "Fastus: Acascaded Finite-State Transducer for Extracting Information from Natural-Language Text," presented at MUC, Cambridge, MA, 1997.
[20] S. Wasi, Z. Shaikh, and J. Shamsi, "Contextual Event Information Extractor for Emails," SURJ, 2011.
[21] C.-N. Seon, H. Kim, and H. Kim, "Information Extraction Using Finite State Automata and Syllable N-Gramsin a Mobile Environment," presented at ACL-08: HLT Workshop on Mobile Language Processing, Ohio, USA, 2008.