The Inception Team at NSURL-2019 Task 8: Semantic Question Similarity in Arabic
Hana Al-Theiabat, Aisha Al-Sadi
Abstract
This paper describes our method for the task of Semantic Question Similarity in Arabic in the workshop on NLP Solutions for Under-Resourced Languages (NSURL). The aim is to build a model that is able to detect similar semantic questions in the Arabic language for the provided dataset. Different methods of determining questions similarity are explored in this work. The proposed models achieved high F1-scores, which range from (88% to 96%). Our official best result is produced from the ensemble model of using a pre-trained multilingual BERT model with different random seeds with 95.924% F1-Score, which ranks the first among nine participants teams.
Results
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Question Similarity | Q2Q Arabic Benchmark | F1 score | 0.95924 | Ensemble multilingual BERT model |
Related Papers
KCluster: An LLM-based Clustering Approach to Knowledge Component Discovery2025-05-09Personalized LLM for Generating Customized Responses to the Same Query from Different Users2024-12-16Detecting Redundant Health Survey Questions Using Language-agnostic BERT Sentence Embedding (LaBSE)2024-12-05QEQR: An Exploration of Query Expansion Methods for Question Retrieval in CQA Services2024-11-23Learning Metadata-Agnostic Representations for Text-to-SQL In-Context Example Selection2024-10-17Aspect-oriented Consumer Health Answer Summarization2024-05-10DAGKT: Difficulty and Attempts Boosted Graph-based Knowledge Tracing2022-10-18QSTS: A Question-Sensitive Text Similarity Measure for Question Generation2022-10-01