Institution profile

Heriot-Watt University

Academic institutioneurope · gb
Official website
Research library237linked papers
Opportunities0open roles
Selected work

Representative Papers

Cross-lingual Offensive Language Detection: A Systematic Review of Datasets, Transfer Approaches and Challenges

Jan 17, 2024arXiv.org

This paper addresses the challenge of cross-lingual offensive language detection in social media. We systematically review 67 studies, with the first comprehensive focus on cross-lingual transfer learning (CLTL) methods for this task. Methodologically, we propose a holistic classification framework tailored to CLTL, innovatively categorizing approaches by “transfer object” into three paradigms: instance-level, feature-level, and parameter-level transfer. We construct and publicly release two structured resource tables, comprehensively cataloging multilingual pre-trained models, dictionary-based alignment techniques, zero-/few-shot transfer strategies, and adversarial training methods. Key challenges—including linguistic imbalance, annotation scarcity, and cultural context deficiency—are distilled and analyzed. The work yields a reusable research roadmap and an open resource repository, providing both theoretical foundations and practical tools for cross-lingual harmful content governance.

5 citationsRead paper

A Generalised Framework for Property-Driven Machine Learning

May 01, 2025

Neural networks often fail to satisfy formal properties required in safety-critical applications. Method: This paper proposes an attribute-driven unified training framework that jointly integrates geometric constraints from adversarial training (generalized hyperrectangular input domains) and semantic constraints encoded via differentiable first-order logic, thereby translating arbitrary formal properties into differentiable loss terms. The framework jointly optimizes a property-weighted loss function and neural network controllers. Contribution/Results: It enables concurrent assurance of robustness and correctness under flexible, domain-specific regional specifications across diverse fields (e.g., control systems, NLP). Evaluated on a neural controller for unmanned aerial vehicles, the framework achieves significant improvement in formal property satisfaction rates. Open-sourced and fully reproducible, it supports a broad range of canonical formal properties, demonstrating strong generalizability and plug-and-play usability.

1 citations1 influentialRead paper

Neural Network Verification for Gliding Drone Control: A Case Study

May 01, 2025

This work addresses the formal robustness verification of a neural-network-based trajectory tracking controller for centimeter-scale biomimetic gliding micro-air vehicles—inspired by *Alsomitra macrocarpa* seeds—to fill a critical gap in verification methodologies for micro-air vehicles operating under passive wind transport. We propose a novel robust training framework tailored for regression-type neural networks, construct the first verified neural network (VNN) benchmark case for gliding micro-air vehicles, and integrate vehicle dynamics simulation (Vehicle), reachability analysis (CORA), and high-fidelity aerodynamic modeling. Experimental results demonstrate that our training method substantially improves both tracking accuracy and robustness of the closed-loop system. Moreover, the study exposes systematic limitations of existing VNN verification tools when applied to highly nonlinear, physics-driven dynamical systems. Collectively, these contributions establish a scalable, physics-informed methodology for engineering-grade safety verification of autonomous micro-air vehicles.

1 citationsRead paper

Boosting Short Text Classification with Multi-Source Information Exploration and Dual-Level Contrastive Learning

Jan 16, 2025

To address the classification performance bottleneck caused by semantic sparsity in short texts and scarcity of labeled data, this paper proposes MI-DELIGHT: a model that represents short texts as multi-source enhanced graphs—integrating statistical co-occurrence, linguistic structure, and knowledge facts—and employs dual-granularity contrastive learning (instance-level and cluster-level) to strengthen discriminative representation learning. Furthermore, it introduces a hierarchical task correlation architecture that explicitly models dependency relationships between primary and auxiliary tasks. Key innovations include: (i) the first multi-source information协同 graph construction mechanism, (ii) a novel dual-granularity contrastive learning paradigm, and (iii) an interpretable hierarchical task modeling framework. Extensive experiments demonstrate that MI-DELIGHT significantly outperforms state-of-the-art methods across multiple standard short-text classification benchmarks; notably, in several low-resource settings, it even surpasses mainstream large language models.

1 citationsRead paper
Recent publications

Latest Papers