College of Computing and Mathematics
Information & Computer Science Department
Presents an Online Seminar
Enhancing Arabic Keyphrase Extraction Deep Learning Models with Pre-trained Contextual Embedding and External Features
Date: Wednesday, 13th April, 2022
Time: 02:30 pm – 3:10 pm
Location: MS Teams: Link: Link to the meeting
Mrs. Randah Alharbi,
PhD Student, ICS Dept.
Keyphrase extraction is essential to many Information retrieval (IR) and Natural language Processing (NLP) tasks such as summarization and indexing. In this study, we investigate state-of-the-art approaches to keyphrase extraction on Arabic. We address the problem as sequence classifications and create a Bi-LSTM model to classify each token of the sequence to either part of the keyphrase or outside of any keyphrase. We extracted word embeddings from two pre-trained model which are Word2Vec and BERT. Moreover, we investigated the effect of incorporating linguistic, positional, and statistical features with word embeddings on the performance. Our best performing model has achieved 0.45 F1-score when combining linguistic and positional features with embedding generated from BERT.
Short bio of presenter:
Mrs. Randah Alharbi, A Phd candidate at KFUPM, MSc of Artificial intelligence, Interested on Arabic NLP.
All faculty, researchers and graduate students are invited to attend.
Information & Computer Science Department, College of Computing and Mathematics
Telephone: +966 (13) 860 2175, Email: email@example.com, Website: www.kfupm.edu.sa/departments/ics/
Copyright © 2014 King Fahd University of Petroleum & Minerals