Nikolaos Pappas

large language model (4) hierarchical attention (3) neural machine translation (3) representation learning (3) recurrent neural network (3) encoder-decoder architecture (2) hallucination detection (2) linear attention (2) efficient computing (2) document-level translation (2) automatic speech recognition (2) multi-task learning (2) transformer architecture (2) in-context learning (2) semantic parsing (2) machine translation (2) inference efficiency (2) attention mechanism (2) embedding space (1) transfer learning (1)