no code implementations • 11 Jan 2024 • Adrian Gheorghiu, Iulian-Marius Tăiatu, Dumitru-Clementin Cercel, Iuliana Marin, Florin Pop
As the RoCoLe dataset is imbalanced and does not have many samples, fine-tuning of pre-trained models and multiple augmentation techniques need to be used.
no code implementations • 30 Dec 2023 • Sebastian-Vasile Echim, Iulian-Marius Tăiatu, Dumitru-Clementin Cercel, Florin Pop
Through our experiments, we determine that on a benchmark dataset, the robustness can be the price of the classification accuracy with performance reductions of 3%-20% for regular tests and gains of 50%-70% for adversarial attack tests.
no code implementations • 7 Oct 2023 • Emilian-Claudiu Mănescu, Răzvan-Alexandru Smădu, Andrei-Marius Avram, Dumitru-Clementin Cercel, Florin Pop
Lip reading or visual speech recognition has gained significant attention in recent years, particularly because of hardware development and innovations in computer vision.
1 code implementation • 16 Aug 2023 • Vlad-Constantin Lungu-Stan, Dumitru-Clementin Cercel, Florin Pop
By adding classification heads at each level of the transformer and employing a cascading distillation process, we improve the balanced multi-class accuracy of the base model by 2. 1%, while creating a range of models of various sizes but comparable performance.
no code implementations • 4 Aug 2023 • Răzvan-Alexandru Smădu, Sebastian-Vasile Echim, Dumitru-Clementin Cercel, Iuliana Marin, Florin Pop
In the current work, we explore the effects of various unsupervised domain adaptation techniques between two text classification tasks: fake and hyperpartisan news detection.
no code implementations • 13 Jun 2023 • Sebastian-Vasile Echim, Răzvan-Alexandru Smădu, Andrei-Marius Avram, Dumitru-Clementin Cercel, Florin Pop
Satire detection and sentiment analysis are intensively explored natural language processing (NLP) tasks that study the identification of the satirical tone from texts and extracting sentiments in relationship with their targets.
no code implementations • 11 Jun 2023 • Iulian-Marius Tăiatu, Andrei-Marius Avram, Dumitru-Clementin Cercel, Florin Pop
Developing natural language processing (NLP) systems for social media analysis remains an important topic in artificial intelligence research.
no code implementations • 30 Dec 2022 • Răzvan-Alexandru Smădu, George-Eduard Zaharia, Andrei-Marius Avram, Dumitru-Clementin Cercel, Mihai Dascalu, Florin Pop
Keyphrase identification and classification is a Natural Language Processing and Information Retrieval task that involves extracting relevant groups of words from a given text related to the main topic.
no code implementations • RANLP 2017 • Dumitru-Clementin Cercel, Cristian Onose, Stefan Trausan-Matu, Florin Pop
Understanding questions and answers in QA system is a major challenge in the domain of natural language processing.