Top Publications

You can also find my articles on my Google Scholar profile.

RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive Learning

Published in North American Chapter of the Association for Computational Linguistics, 2024

This paper introduces RobustSentEmbed, a method for obtaining robust sentence embeddings through an iterative collaboration between an adversarial perturbation generator and a PLM-based encoder. By generating high-risk perturbations in both token-level and sentence-level embedding spaces, RobustSentEmbed employs a contrastive learning objective combined with a token replacement detection objective to enhance similarity between original and adversarial embeddings.

Recommended citation: Javad Rafiei Asl, Prajwal Panzade, Eduardo Blanco, Daniel Takabi, Zhipeng Cai. "RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive Learning" North American Chapter of the Association for Computational Linguistics (NAACL 2024). https://arxiv.org/abs/2403.11082

A Semantic, Syntactic, And Context-Aware Natural Language Adversarial Example Generator

Published in IEEE Transactions on Dependable and Secure Computing, 2024

The paper presents SSCAE, a novel method for crafting high-quality adversarial examples (AEs) in natural language processing (NLP). SSCAE utilizes a masked language model to identify key words and generate substitutions, which are then evaluated by two language models for semantic and syntactic accuracy. Incorporating dynamic thresholds and local greedy search, SSCAE efficiently generates imperceptible AEs that maintain semantic and syntactic consistency.

Recommended citation: Javad Rafiei Asl, Mohammad H. Rafiei, Manar Alohaly, and Daniel Takabi. "A Semantic, Syntactic, And Context-Aware Natural Language Adversarial Example Generator." IEEE Transactions on Dependable and Secure Computing (2024). https://ieeexplore.ieee.org/abstract/document/10416371

RobustEmbed: Robust Sentence Embeddings Using Self-Supervised Contrastive Pre-Training

Published in Empirical Methods in Natural Language Processing: EMNLP Findings, 2023

The paper proposes RobustEmbed, a self-supervised sentence embedding framework aimed at enhancing both generalization and robustness in text representation tasks and adversarial scenarios. By generating high-risk adversarial perturbations and leveraging a novel contrastive objective approach, RobustEmbed effectively learns high-quality sentence embeddings.

Recommended citation: Javad Rafiei Asl, Eduardo Blanco, and Daniel Takabi. "RobustEmbed: Robust Sentence Embeddings Using Self-Supervised Contrastive Pre-Training." In The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023). https://aclanthology.org/2023.findings-emnlp.305

TSAKE: A topical and structural automatic keyphrase extractor

Published in Applied Soft Computing, 2017

This paper introduces TSAKE, a novel approach for automatic keyphrase extraction that leverages both N-gram topical models and co-occurrence graphs. Unlike traditional methods, TSAKE weights edges in the co-occurrence graph using the topic model and applies network analysis to identify finer-grained sub-topics. By incorporating these insights, TSAKE outperforms baseline techniques and state-of-the-art models in keyphrase extraction tasks.

Recommended citation: Javad Rafiei-Asl, and Ahmad Nickabadi. "TSAKE: A topical and structural automatic keyphrase extractor." Applied soft computing 58 (2017): 620-630. https://doi.org/10.1016/j.asoc.2017.05.014

Source retrieval plagiarism detection based on noun phrase and keyword phrase extraction

Published in In Proceedings of the Conference and Labs of the Evaluation Forum and Workshop (CLEF’15), 2015

This paper addresses the task of source retrieval from a large textual documents corpus. It introduces two methods for extracting important terms: weighted noun phrases and keyword phrases from lengthy sentences based on word count. Queries are formed from top-ranked sentences, and the system collects a comprehensive dataset of downloaded sources for query filtering. Each query is divided into two sub-queries, and the system extracts one snippet for each sub-query for downloading.

Recommended citation: Javad Rafiei Asl, Salar Mohtaj, Vahid Zarrabi, and Habibollah Asghari. "Source retrieval plagiarism detection based on noun phrase and keyword phrase extraction—Notebook for PAN at CLEF 2015." In Proceedings of the Conference and Labs of the Evaluation Forum and Workshop (CLEF’15). 2015. https://ceur-ws.org/Vol-1391/143-CR.pdf