Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings

1 code implementation • 11 Jan 2024 • Hiroaki Yamagiwa, Yusuke Takase, Hidetoshi Shimodaira

Inspired by Word Tour, a one-dimensional word embedding method, we aim to improve the clarity of the word embedding space by maximizing the semantic continuity of the axes.

Word Embeddings

Zero-Shot Edge Detection with SCESAME: Spectral Clustering-based Ensemble for Segment Anything Model Estimation

1 code implementation • 26 Aug 2023 • Hiroaki Yamagiwa, Yusuke Takase, Hiroyuki Kambe, Ryosuke Nakamoto

This paper proposes a novel zero-shot edge detection with SCESAME, which stands for Spectral Clustering-based Ensemble for Segment Anything Model Estimation, based on the recently proposed Segment Anything Model (SAM).

Clustering Edge Detection +1

Discovering Universal Geometry in Embeddings with ICA

1 code implementation • 22 May 2023 • Hiroaki Yamagiwa, Momose Oyama, Hidetoshi Shimodaira

This study utilizes Independent Component Analysis (ICA) to unveil a consistent semantic structure within embeddings of words or images.

Improving word mover's distance by leveraging self-attention matrix

1 code implementation • 11 Nov 2022 • Hiroaki Yamagiwa, Sho Yokoi, Hidetoshi Shimodaira

The proposed method is based on the Fused Gromov-Wasserstein distance, which simultaneously considers the similarity of the word embedding and the SAM for calculating the optimal transport between two sentences.

Paraphrase Identification Semantic Similarity +2