TY - JOUR
T1 - Language processing and learning models for community question answering in Arabic
AU - Romeo, Salvatore
AU - Da San Martino, Giovanni
AU - Belinkov, Yonatan
AU - Barrón-Cedeño, Alberto
AU - Eldesouki, Mohamed
AU - Darwish, Kareem
AU - Mubarak, Hamdy
AU - Glass, James
AU - Moschitti, Alessandro
N1 - Publisher Copyright:
© 2017 Elsevier Ltd
PY - 2019/3
Y1 - 2019/3
N2 - 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.
AB - 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.
KW - Attention models
KW - Community question answering
KW - Constituency parsing in Arabic
KW - Long short-term memory neural networks
KW - Tree-kernel-based ranking
UR - http://www.scopus.com/inward/record.url?scp=85027252939&partnerID=8YFLogxK
U2 - 10.1016/j.ipm.2017.07.003
DO - 10.1016/j.ipm.2017.07.003
M3 - Article
AN - SCOPUS:85027252939
SN - 0306-4573
VL - 56
SP - 274
EP - 290
JO - Information Processing and Management
JF - Information Processing and Management
IS - 2
ER -