Shubhashis Roy Dipta

This paper describes our system developed for SemEval-2024 Task 8, "Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection." Machine-generated texts have been one of the main concerns due to the use of large language models (LLM) in fake text generation, phishing, cheating in exams, or even plagiarizing copyright materials. A lot of systems have been developed to detect machine-generated text. Nonetheless, the majority of these systems rely on the text-generating model, a limitation that is impractical in real-world scenarios, as it’s often impossible to know which specific model the user has used for text generation. In this work, we propose a single model based on contrastive learning, which uses  40% of the baseline’s parameters (149M vs. 355M) but shows a comparable performance on the test dataset (21st out of 137 participants). Our key finding is that even without an ensemble of multiple models, a single base model can have comparable performance with the help of data augmentation and contrastive learning.

Prior work has shown that coupling sequential latent variable models with semantic ontological knowledge can improve the representational capabilities of event modeling approaches. In this work, we present a novel, doubly hierarchical, semi-supervised event modeling framework that provides structural hierarchy while also accounting for ontological hierarchy. Our approach consistsof multiple layers of structured latent variables, where each successive layer compresses and abstracts the previous layers. We guide this compression through the injection of structured ontological knowledge that is defined at the type level of events: importantly, our model allows for partial injection of semantic knowledge and it does not depend on observing instances at any particular level of the semantic ontology. Across two different datasets and four different evaluation metrics, we demonstrate that our approach is able to out-perform the previous state-of-the-art approaches by up to 8.5%, demonstrating the benefits of structured and semantic hierarchical knowledge for event modeling.

Post Transactional Modification (PTM) is a vital process which plays an important role in a wide range of biological interactions. One of the most recently identified PTMs is Malonylation. It has been shown that Malonylation has an important impact on different biological pathways including glucose and fatty acid metabolism. Malonylation can be detected experimentally using mass spectrometry. However, this process is both costly and time-consuming which has inspired research to find more efficient and fast computational methods to solve this problem. This paper proposes a novel approach, called SEMal, to identify Malonylation sites in protein sequences. It uses both structural and evolutionary-based features to solve this problem. It also uses Rotation Forest (RoF) as its classification technique to predict Malonylation sites. To the best of our knowledge, our extracted features as well as our employed classifier have never been used for this problem. Compared to the previously proposed methods, SEMal outperforms them in all metrics such as sensitivity (0.94 and 0.89), accuracy (0.94 and 0.91), and Matthews correlation coefficient (0.88 and 0.82), for Homo Sapiens and Mus Musculus species, respectively. SEMal is publicly available as an online predictor at: http://brl.uiu.ac.bd/SEMal/.