2 papers
cs.CL2023
Good Neighbors Are All You Need for Chinese Grapheme-to-Phoneme Conversion
Jungjun Kim, Changjin Han, Gyuhyeon Nam +1
Most Chinese Grapheme-to-Phoneme (G2P) systems employ a three-stage framework that first transforms input sequences into character embeddings, obtains linguistic information using…
cs.CV2020
Image-to-Image Retrieval by Learning Similarity between Scene Graphs
Sangwoong Yoon, Woo Young Kang, Sungwook Jeon +4
As a scene graph compactly summarizes the high-level content of an image in a structured and symbolic manner, the similarity between scene graphs of two images reflects the relevan…