Семантические Соответствия
task
ID: semanticcorrespondences
Related Papers
A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation
AbstractMulti-modal neural machine translation (NMT) aims to translate source sentences into a target language paired with images. However, dominant multi-modal NMT models do not fully exploit fine-grained semantic correspondences between …...
Learning Semantic Correspondences from Noisy Data-text Pairs by Local-to-Global Alignments
AbstractLearning semantic correspondences between structured input data (e.g., slot-value pairs) and associated texts is a core problem for many downstream NLP applications, e.g., data-to-text generation. Large-scale datasets recently proposed for …...