Language processing and learning models for community question answering in Arabic

Autor: Hamdy Mubarak, Giovanni Da San Martino, Mohamed Eldesouki, James Glass, Alberto Barrón-Cedeño, Alessandro Moschitti, Yonatan Belinkov, Salvatore Romeo, Kareem Darwish
Přispěvatelé: Romeo, Salvatore, Da San Martino, Giovanni, Belinkov, Yonatan, Barrón-Cedeño, Alberto, Eldesouki, Mohamed, Darwish, Kareem, Mubarak, Hamdy, Glass, Jame, Moschitti, Alessandro
Rok vydání: 2019
Předmět:
Community question answering
Long short-term memory neural networks
Deep linguistic processing
Computer science
Attention models
02 engineering and technology
Constituency parsing in Arabic: Tree-kernel-based ranking
Library and Information Sciences
Management Science and Operations Research
computer.software_genre
Ranking (information retrieval)
0202 electrical engineering
electronic engineering
information engineering
Media Technology
Question answering
Constituency parsing in Arabic
Tree-kernel-based ranking
Information retrieval
Parsing
Artificial neural network
business.industry
Community question answeringConstituency parsing in ArabicTree-kernel-based rankingLong short-term memory neural networksAttention models
020206 networking & telecommunications
Pipeline (software)
Computer Science Applications
020201 artificial intelligence & image processing
Artificial intelligence
Tree kernel
business
Long short-term memory neural network
computer
Word (computer architecture)
Natural language processing
Information Systems
Zdroj: Information Processing & Management. 56:274-290
ISSN: 0306-4573
DOI: 10.1016/j.ipm.2017.07.003
Popis: 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.
Databáze: OpenAIRE
Externí odkaz: