1 citations · 1 across the 4 of their papers we have counts for
5 papers · 1 filter
Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine Translation
Heegon Jin, Seonil Son, Jemin Park +3
The advent of scalable deep models and large datasets has improved the performance of Neural Machine Translation. Knowledge Distillation (KD) enhances efficiency by transferring kn…
HaRiM: Evaluating Summary Quality with Hallucination Risk
Seonil Son, Junsoo Park, Jeong-in Hwang +3
One of the challenges of developing a summarization model arises from the difficulty in measuring the factual inconsistency of the generated text. In this study, we reinterpret the…
May the Force Be with Your Copy Mechanism: Enhanced Supervised-Copy Method for Natural Language Generation
Sanghyuk Choi, Jeong-in Hwang, Hyungjong Noh +1
Recent neural sequence-to-sequence models with a copy mechanism have achieved remarkable progress in various text generation tasks. These models addressed out-of-vocabulary problem…
SANVis: Visual Analytics for Understanding Self-Attention Networks
Cheonbok Park, Inyoup Na, Yongjang Jo +7
Attention networks, a deep neural network architecture inspired by humans' attention mechanism, have seen significant success in image captioning, machine translation, and many oth…
Question-Aware Sentence Gating Networks for Question and Answering
Minjeong Kim, David Keetae Park, Hyungjong Noh +2
Machine comprehension question answering, which finds an answer to the question given a passage, involves high-level reasoning processes of understanding and tracking the relevant…