paper-with-me

홈 › Papers

RPD: A Distance Function Between Word Embeddings

2020-05-16 · ACL 2020 6 · Xuhui Zhou, Zaixiang Zheng, Shu-Jian Huang

It is well-understood that different algorithms, training processes, and corpora produce different word embeddings. However, less is known about the relation between different embedding spaces, i.e. how far different sets of embeddings deviate from each other. In this paper, we propose a novel metric called Relative pairwise inner Product Distance (RPD) to quantify the distance between different sets of word embeddings. This metric has a unified scale for comparing different sets of word embeddings. Based on the properties of RPD, we study the relations of word embeddings of different algorithms systematically and investigate the influence of different training processes and corpora. The results shed light on the poorly understood word embeddings and justify RPD as a measure of the distance of embedding spaces.

📄 PDF Abstract BibTeX arXiv:2005.08113

Code (0)

등록된 구현이 없습니다.

Tasks

Word Embeddings

Similar Papers 제목 키워드 기반

Distilled Wasserstein Learning for Word Embedding and Topic Modeling

2018-09-12 · NeurIPS 2018 12 · Hongteng Xu, Wenlin Wang, Wei Liu, Lawrence Carin

We propose a novel Wasserstein method with a distillation mechanism, yielding joint learning of word embeddings and topics. The proposed method is based on the fact that the Euclidean distance between word embeddings may…

Mortality PredictionWord Embeddings

Speeding up Word Mover's Distance and its variants via properties of distances between embeddings

2019-12-01 · Matheus Werner, Eduardo Laber

The Word Mover's Distance (WMD) proposed by Kusner et al. is a distance between documents that takes advantage of semantic relations among words that are captured by their embeddings. This distance proved to be quite eff…

Document ClassificationGeneral Classification

Distance-to-Distance Ratio: A Similarity Measure for Sentences Based on Rate of Change in LLM Embeddings

2026-01-25 · Abdullah Qureshi, Kenneth Rice, Alexander Wolpert arxiv

A measure of similarity between text embeddings can be considered adequate only if it adheres to the human perception of similarity between texts. In this paper, we introduce the distance-to-distance ratio (DDR), a novel…

Angular-Based Word Meta-Embedding Learning

2018-08-13 · James O' Neill, Danushka Bollegala

Ensembling word embeddings to improve distributed word representations has shown good success for natural language processing tasks in recent years. These approaches either carry out straightforward mathematical operatio…

Meta-LearningWord EmbeddingsWord Similarity

A Theoretical Framework for Acoustic Neighbor Embeddings

2024-12-03 · Woojay Jeon

This paper provides a theoretical framework for interpreting acoustic neighbor embeddings, which are representations of the phonetic content of variable-width audio or text in a fixed-dimensional embedding space. A proba…

Clustering