2024/03/17 · To handle asymmetric relationships between sen- tences, we fine-tune pre-trained language models for representing sentences as Gaussian ...

2023/05/22 · This paper proposes GaussCSE, a Gaussian distribution-based contrastive learning framework for sentence embedding that can handle asymmetric ...

5 日前 · Yoda, S., Tsukagoshi, H., Sasano, R., and Takeda, K. (2024). “Sentence Representations via Gaussian Embedding.” In Proceedings of the 18th ...

2024/09/03 · 本稿では，EACL2024 に採択された論文 “Sentence Representations via Gaussian Embedding”. (Yoda et al. 2024) について解説する．

2023/10/16 · This paper proposes GaussCSE, a Gaussian-distribution-based contrastive learning framework for sentence embedding that can handle asymmetric ...

GaussCSE is a method to obtain Gaussian embeddings of sentences by fine-tuning a pre-trained language model through contrastive learning. In this section, we ...

GaussCSE is proposed, a Gaussian-distribution-based contrastive learning framework for sentence embedding that can handle asymmetric inter-sentential ...

近年、文の持つ情報を埋め込み空間上の点として. 表現する文ベクトルの研究が盛んである。しかし、. 点による文の表現は、文の持つ意味の広がりや包含.

GaussCSE. This repository contains the fune-tune and evaluation code for our paper Sentence Representations via Gaussian Embedding. Getting started. Prepare ...

This paper advocates for density-based distributed embeddings and presents a method for learning representations in the space of Gaussian distributions. We ...