TY - GEN
T1 - Design of question answering system with automated question generation
AU - Kim, Min Kyoung
AU - Kim, Han Joon
PY - 2008
Y1 - 2008
N2 - One of the most difficult problems in developing question-answering (QA) system is that it is so hard to generate natural language questions and to find an answer to a query question. In order to avoid a number of difficulties of developing QA systems, we propose a new style of question-answering system architecture that actively uses sentences within a document as a source of question/answer. Basically, our proposed QA system gives user a set of candidate query question for user information needs, and the candidate questions are automatically generated from significant sentences that are expected to contain meaningful facts or events. The QA system builds a complete database of (question, answer) pairs after analyzing a whole collection of documents. For this, we need to perform the following steps: sentence split, named-entity recognition, question generation, question filtering, question/answer indexing. The important things in the process are question generation and question filtering. For the first thing, we can generate questions that ask the entities extracted from a given sentence. The question filtering is to isolate significant sentences that have meaningful information that users want.
AB - One of the most difficult problems in developing question-answering (QA) system is that it is so hard to generate natural language questions and to find an answer to a query question. In order to avoid a number of difficulties of developing QA systems, we propose a new style of question-answering system architecture that actively uses sentences within a document as a source of question/answer. Basically, our proposed QA system gives user a set of candidate query question for user information needs, and the candidate questions are automatically generated from significant sentences that are expected to contain meaningful facts or events. The QA system builds a complete database of (question, answer) pairs after analyzing a whole collection of documents. For this, we need to perform the following steps: sentence split, named-entity recognition, question generation, question filtering, question/answer indexing. The important things in the process are question generation and question filtering. For the first thing, we can generate questions that ask the entities extracted from a given sentence. The question filtering is to isolate significant sentences that have meaningful information that users want.
UR - http://www.scopus.com/inward/record.url?scp=57849114430&partnerID=8YFLogxK
U2 - 10.1109/NCM.2008.236
DO - 10.1109/NCM.2008.236
M3 - Conference contribution
AN - SCOPUS:57849114430
SN - 9780769533223
T3 - Proceedings - 4th International Conference on Networked Computing and Advanced Information Management, NCM 2008
SP - 365
EP - 368
BT - Proceedings - 4th International Conference on Networked Computing and Advanced Information Management, NCM 2008
T2 - 4th International Conference on Networked Computing and Advanced Information Management, NCM 2008
Y2 - 2 September 2008 through 4 September 2008
ER -