Sentence Representations via Gaussian Embedding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yoda, Shohei, Tsukagoshi, Hayato, Sasano, Ryohei, Takeda, Koichi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929248960249856
author Yoda, Shohei
Tsukagoshi, Hayato
Sasano, Ryohei
Takeda, Koichi
author_facet Yoda, Shohei
Tsukagoshi, Hayato
Sasano, Ryohei
Takeda, Koichi
contents Recent progress in sentence embedding, which represents the meaning of a sentence as a point in a vector space, has achieved high performance on tasks such as a semantic textual similarity (STS) task. However, sentence representations as a point in a vector space can express only a part of the diverse information that sentences have, such as asymmetrical relationships between sentences. This paper proposes GaussCSE, a Gaussian distribution-based contrastive learning framework for sentence embedding that can handle asymmetric relationships between sentences, along with a similarity measure for identifying inclusion relations. Our experiments show that GaussCSE achieves the same performance as previous methods in natural language inference tasks, and is able to estimate the direction of entailment relations, which is difficult with point representations.
format Preprint
id arxiv_https___arxiv_org_abs_2305_12990
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Sentence Representations via Gaussian Embedding
Yoda, Shohei
Tsukagoshi, Hayato
Sasano, Ryohei
Takeda, Koichi
Computation and Language
Recent progress in sentence embedding, which represents the meaning of a sentence as a point in a vector space, has achieved high performance on tasks such as a semantic textual similarity (STS) task. However, sentence representations as a point in a vector space can express only a part of the diverse information that sentences have, such as asymmetrical relationships between sentences. This paper proposes GaussCSE, a Gaussian distribution-based contrastive learning framework for sentence embedding that can handle asymmetric relationships between sentences, along with a similarity measure for identifying inclusion relations. Our experiments show that GaussCSE achieves the same performance as previous methods in natural language inference tasks, and is able to estimate the direction of entailment relations, which is difficult with point representations.
title Sentence Representations via Gaussian Embedding
topic Computation and Language
url https://arxiv.org/abs/2305.12990