7 citations · 8 across the 14 of their papers we have counts for
3 papers · 1 filter
Contrastive Knowledge Distillation for Robust Multimodal Sentiment Analysis
Zhongyi Sang, Kotaro Funakoshi, Manabu Okumura
Multimodal sentiment analysis (MSA) systems leverage information from different modalities to predict human sentiment intensities. Incomplete modality is an important issue that ma…
Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translation
Boxuan Lyu, Hidetaka Kamigaito, Kotaro Funakoshi +1
Maximum a posteriori decoding, a commonly used method for neural machine translation (NMT), aims to maximize the estimated posterior probability. However, high estimated probabilit…
DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation
Aru Maekawa, Satoshi Kosugi, Kotaro Funakoshi +1
Dataset distillation aims to compress a training dataset by creating a small number of informative synthetic samples such that neural networks trained on them perform as well as th…