Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Analyzing Linguistic Features for Answer Re-Ranking of Why-Questions

Analyzing Linguistic Features for Answer Re-Ranking of Why-Questions
View Sample PDF
Author(s): Manvi Breja (National Institute of Technology, Kurukshetra, India) and Sanjay Kumar Jain (National Institute of Technology, Kurukshetra, India)
Copyright: 2022
Volume: 24
Issue: 3
Pages: 16
Source title: Journal of Cases on Information Technology (JCIT)
Editor(s)-in-Chief: Andrew Borchers (Lipscomb University, USA)
DOI: 10.4018/JCIT.20220701.oa10


View Analyzing Linguistic Features for Answer Re-Ranking of Why-Questions on the publisher's website for pricing and purchasing information.


Why-type non-factoid questions are ambiguous and involve variations in their answers. A challenge in returning one appropriate answer to user requires the process of appropriate answer extraction, re-ranking and validation. There are cases where the need is to understand the meaning and context of a document rather than finding exact words involved in question. The paper addresses this problem by exploring lexico-syntactic, semantic and contextual query-dependent features, some of which are based on deep learning frameworks to depict the probability of answer candidate being relevant for the question. The features are weighted by the score returned by ensemble ExtraTreesClassifier according to features importance. An answer re-ranker model is implemented that finds the highest ranked answer comprising largest value of feature similarity between question and answer candidate and thus achieving 0.64 Mean Reciprocal Rank (MRR). Further, answer is validated by matching the answer type of answer candidate and returns the highest ranked answer candidate with matched answer type to a user.

Related Content

Raya Basil Alothman, Imad Ibraheem Saada, Basma Salim Bazel Al-Brge. © 2022. 18 pages.
Abdulraheem Jamil Ahmed, Falah Hasan Mohammed, Naji Abdullah Majedkan. © 2022. 11 pages.
Saravanan S., Sujitha Juliet. © 2022. 14 pages.
Raed Fadel Jawid. © 2022. 18 pages.
Ahmed Jasim Hameed, Anfal S. Shareef, Sameer Imad Shaban. © 2022. 12 pages.
Mona Tanwar, Sunil Kumar Khatri, Ravi Pendse. © 2022. 16 pages.
Manvi Breja, Sanjay Kumar Jain. © 2022. 16 pages.
Body Bottom