Language processing and learning models for community question answering in Arabic |
| |
| Institution: | 1. Qatar Computing Research Institute, HBKU, Doha, Qatar;2. MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA;1. School of Computing Science, University of Glasgow, UK;2. Urban Big Data Centre, University of Glasgow, UK;3. Department of Computer & Information Sciences, University of Strathclyde, UK;1. Institute of Informatics, Hacettepe University, Turkey;2. Department of Computer Engineering, Hacettepe UniversityBeytepe Campus P.O. 06800, Ankara, Turkey;1. Kuwait University, Kuwait;2. University of Manchester, England, United Kingdom;1. Faculty of Computer Science & Information Technology, University of Malaya, Malaysia;2. Department of Computer Engineering, College of Computer Science and Engineering, NOOR Research Center, Taibah University, Saudi Arabia;3. Department of Computer Engineering, College of Computer Science, Shaqra University, Saudi Arabia;1. Department of Computer and Information Sciences, Northumbria University, Newcastle Upon Tyne, NE1 9ST, UK;2. Department of Computer Science and Engineering, Collage of Engineering, Qatar University, Doha, 2713, Qatar;3. School of Computing, Staffordshire University, Stoke on Trent, UK |
| |
| Abstract: | In this paper we focus on the problem of question ranking in community question answering (cQA) forums in Arabic. We address the task with machine learning algorithms using advanced Arabic text representations. The latter are obtained by applying tree kernels to constituency parse trees combined with textual similarities, including word embeddings. Our two main contributions are: (i) an Arabic language processing pipeline based on UIMA—from segmentation to constituency parsing—built on top of Farasa, a state-of-the-art Arabic language processing toolkit; and (ii) the application of long short-term memory neural networks to identify the best text fragments in questions to be used in our tree-kernel-based ranker. Our thorough experimentation on a recently released cQA dataset shows that the Arabic linguistic processing provided by Farasa produces strong results and that neural networks combined with tree kernels further boost the performance in terms of both efficiency and accuracy. Our approach also enables an implicit comparison between different processing pipelines as our tests on Farasa and Stanford parsers demonstrate. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
