Answer Extraction Based on Merging Score Strategy of Hot Terms

LE Juan; ZHANG Chunxia; NIU Zhendong

doi:10.1049/cje.2016.06.028

Volume 25 Issue 4

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2016 > 25(4): 614-620

LE Juan, ZHANG Chunxia, NIU Zhendong, “Answer Extraction Based on Merging Score Strategy of Hot Terms,” Chinese Journal of Electronics, vol. 25, no. 4, pp. 614-620, 2016, doi: 10.1049/cje.2016.06.028

Citation:

LE Juan, ZHANG Chunxia, NIU Zhendong, “Answer Extraction Based on Merging Score Strategy of Hot Terms,” Chinese Journal of Electronics, vol. 25, no. 4, pp. 614-620, 2016, doi: 10.1049/cje.2016.06.028

Citation:

PDF( 243 KB)

Answer Extraction Based on Merging Score Strategy of Hot Terms

doi: 10.1049/cje.2016.06.028

1.
School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China;
2.
School of Software, Beijing Institute of Technology, Beijing 100081, China;
3.
Beijing Engineering Research Center of Massive Language Information Processing and Cloud Computing Application, Beijing Institute of Technology, Beijing 100081, China

Funds: This work is supported by the National Natural Science Foundation of China (No.61370137, No.61272361), the National Basic Research Program of China (973 Program) (No.2012CB720702), and the Ministry of Education in China Project of Humanities and Social Sciences (No.13YJC870011).

More Information

Corresponding author: NIU Zhendong (corresponding author) was born in 1968, Ph.D. supervisor, professor. His research areas include digital library, information retrieval, e-learning and neuroinformatics. (Email:zniu@bit.edu.cn)
Received Date: 2014-05-26
Rev Recd Date: 2014-10-16
Publish Date: 2016-07-10

Abstract

Abstract

Answer extraction (AE) is one of the key technologies in developing the open domain Question & answer (Q&A) system. Its task is to yield the highest score to the expected answer based on an effective answer score strategy. We introduce an answer extraction method by Merging score strategy (MSS) based on hot terms. The hot terms are defined according to their lexical and syntactic features to highlight the role of the question terms. To cope with the syntactic diversities of the corpus, we propose four improved candidate answer score algorithms. Each of them is based on the lexical function of hot terms and their syntactic relationships with the candidate answers. Two independent corpus score algorithms are proposed to tap the role of the corpus in ranking the candidate answers. Six algorithms are adopted in MSS to tap the complementary action among the corpus, the candidate answers and the questions. Experiments demonstrate the effectiveness of the proposed strategy.
- Question & answer (Q&A),
- Answer extraction (AE),
- Merging score strategy (MSS),
- Hot terms

FullText(HTML)

References(11)

References

D.A. Ferrucci, "Introduction to ‘This is Watson’ ", IBM Journal of Research and Development, Vol.56, No.3/4, Paper 1, pp.1:1-1:15, 2012.

S.C. Yang, C. Gao, X.Y. Dai, et al., "Combining features of question based on diversity and importance", Acta Electronica Sinica, Vol.42, No.5, pp.918-924, 2014. (in Chinese)

D. Ravichandran and E. Hovy, "Learning surface text patterns for a question answering system", Proc. of the 40th Annual Meeting of the Association for Computational Linguistics, New York, USA, pp.32-36, 1998.

D. Shen, G.M. Kruijff and D. Klakow, "Exploring syntactic relation patterns for question answering", Proc. of the Second International Joint Conference on Natural Language Processing, Jeju Island, Republic of Korea, pp.507-518, 2005.

H. Cui, R.X. Sun, K.Y. Li, et al., "Question answering passage retrieval using dependency relations", Proc. of the 28th ACM-SIGIR International Conference on Research and Development in Information Retrieval, Salvador, Brazil, pp.400-407, 2005.

D. Shen and D. Klakow, "Exploring correlation of dependency relation paths for answer extraction", Proc. of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Sydney, Australia, pp.889-896, 2006.

M.C. McCord, J.W. Murdock and B.K. Boguraev, "Deep parsing in Watson", IBM Journal of Research and Development, Vol.56, No.3/4, Paper 3, pp.3:1-3:15, 2012.

A. Sun, Y.J. Ma and M.H. Jiang, "A maximum entropy model based answer extraction for Chinese question answering", Proc. of the 8th International Conference on Signal Processing, Beijing, China, pp.1239-1248, 2006.

B.S. Hu, D.L. Wang, G. Yu, et al., "An answer extraction algorithm based on syntax structure feature parsing and classification", Chinese Journal of Computers, Vol.31, No.4, pp.662-676, 2008. (in Chinese)

H. Sun, N. Duan, Y.J. Duan, et al., "Answer extraction from passage graph for question answering", Proc. of the 23rd International Joint Conference on Artificial Intelligence, Beijing, China, pp.32-36, 2013.

Y.Z. Wu, J. Zhao and B. Xu, "Unsupervised answer pattern acquisition", Journal of Chinese Information Processing, Vol.21, No.2, pp.69-76, 2007. (in Chinese)

Relative Articles

Supplements(0)

Cited By

Proportional views