4 papers
Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning
Mahdi Khodabandeh, Ghazal Shabani, Arash Yousefi Jordehi +1
Efficient lossless compression is essential for minimizing storage costs and transmission overhead while preserving data integrity. Traditional compression techniques, such as dict…
From Semantic Roles to Opinion Roles: SRL Data Extraction for Multi-Task and Transfer Learning in Low-Resource ORL
Amirmohammad Omidi Galdiani, Sepehr Rezaei Melal, Mohammad Norasteh +2
This report presents a detailed methodology for constructing a high-quality Semantic Role Labeling (SRL) dataset from the Wall Street Journal (WSJ) portion of the OntoNotes 5.0 cor…
Active Few-Shot Learning for Text Classification
Saeed Ahmadnia, Arash Yousefi Jordehi, Mahsa Hosseini Khasheh Heyran +3
The rise of Large Language Models (LLMs) has boosted the use of Few-Shot Learning (FSL) methods in natural language processing, achieving acceptable performance even when working w…
Views Are My Own, but Also Yours: Benchmarking Theory of Mind Using Common Ground
Adil Soubki, John Murzaku, Arash Yousefi Jordehi +4
Evaluating the theory of mind (ToM) capabilities of language models (LMs) has recently received a great deal of attention. However, many existing benchmarks rely on synthetic data,…