Work

QU-BIGIR at SemEval 2017 Task 3: Using Similarity Features for Arabic Community Question Answering Forums

Year: 2017

Type: conference-paper

Abstract: In this paper, we describe our QU-BIGIR system for the Arabic subtask D of the Se-mEval 2017 Task 3. Our approach builds on our participation in the past version of the same subtask.This year, our system uses different similarity features that encodes lexical and semantic pairwise similarity of text pairs.In addition to wellknown similarity measures such as cosine similarity, we use other measures based on the summary statistics of word embedding representation for a given text.To rank a list of candidate question-answer pairs for a given question, we train a linear SVM classifier over our similarity features.Our best resulting run came second in subtask D with a very competitive performance to the first-ranking system.

Source: International Workshop on Semantic Evaluation (SemEval)

DOI: 10.18653/v1/s17-2059

Authors: Marwan Torki, Maram Hasanain, Tamer Elsayed

Institution: Qatar University

Language: English

Topic: Expert finding and Q&A systems

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Qatar Foundation, Fonds National de la Recherche Luxembourg, Qatar National Research Fund

Award: G6018914484