Chris Pollett > Students > Shenoy
[Bio] [Blog] [Refactor Code and support Localization] [Del 3: Best Answer at the Top] |
CS297 ProposalImproving an Open Source Question Answering SystemSalil Shenoy (salil.shenoy@sjsu.edu) Advisor: Dr. Chris Pollett Description: Yioop is an open source search engine developed and managed by Dr. Chris Pollett. Currently, when a query is searched, it suggests relevant documents based on the query. An existing patch for the Question Answering system was developed by Niravkumar Patel, the existing module supports queries in English. I will work on understanding and improving the existing patch and try to improve the Question Answering system. I intend to leverage natural language processing and enhance the module so that it supports internationalization. The Question Answering system developed should be able to identify the users query and retrieve information efficiently. Schedule:
Deliverables: The full project will be done when CS298 is completed. The following will be done by the end of CS297: 1. Get existing patch to work with the current version of Yioop. 2. Literature review for Question Answering System. 3. Create a part of speech tagger for a particular language (examples: Hindi, Marathi) 4. Refactor the tokenization code for English QA system 5. CS 297 Report. References: Yioop Documentation Yioop Documentation Question Answer System in Information Retrieval Question Answer System Wiki [2015] Existing work done on Question Answer System Question-Answer System patch for Yioop by Niravkumar Patel, 2015. [2015] Information Extraction From Text Information Extraction From Text by Steven Bird, Ewan Klein, and Edward Loper 2015 [2007] Triplet Extraction From Sentences by Delia Rusu, Lorand Dali, Bla Fortuna, Marko Grobelnik, Dunja Mladeni. 2007. [2003] Integrating Web-based and Corpus-based Techniques for Question Answering by Boris Katz, Jimmy Lin, Daniel Loreto, Wesley Hildebrandt, Matthew Bilotti, Sue Felshin, Aaron Fernandes, Gregory Marton, Federico Mora. TREC 2003. [2001] Gathering Knowledge for a Question Answering System from Heterogeneous Information Sources by Boris Katz and Jimmy Lin and Sue Felshin. ACL Workshop 2001. [2005] A Hindi Question Answering system for E-learning documents by Praveen Kumar et.al [2003] A light weight Hindi stemmer by A. Ramanathan, D. D. Rao S. Sahu, N. Vasnik, and D. Roy, "PRASHNOTTAR: A HINDI QUESTION ANSWERING SYSTEM," International Journal of Computer Science and Information Technology (IJCSIT), vol. 4, no. 2, pp. 149-158, Apr. 2012. Hindi Sentence Structure [Online] Available: http://hindilanguage.info/hindi-grammar/syntax/ |