paper-with-me

홈 › Papers

Persistence Homology of TEDtalk: Do Sentence Embeddings Have a Topological Shape?

2021-03-25 · Shouman Das, Syed A. Haque, Md. Iftekhar Tanveer

\emph{Topological data analysis} (TDA) has recently emerged as a new technique to extract meaningful discriminitve features from high dimensional data. In this paper, we investigate the possibility of applying TDA to improve the classification accuracy of public speaking rating. We calculated \emph{persistence image vectors} for the sentence embeddings of TEDtalk data and feed this vectors as additional inputs to our machine learning models. We have found a negative result that this topological information does not improve the model accuracy significantly. In some cases, it makes the accuracy slightly worse than the original one. From our results, we could not conclude that the topological shapes of the sentence embeddings can help us train a better model for public speaking rating.

📄 PDF Abstract BibTeX arXiv:2103.14131

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceSentence EmbeddingsTopological Data Analysis

Similar Papers 제목 키워드 기반

$k$-Means Clustering for Persistent Homology

2022-10-18 · Yueqi Cao, Prudence Leung, Anthea Monod

Persistent homology is a methodology central to topological data analysis that extracts and summarizes the topological features within a dataset as a persistence diagram; it has recently gained much popularity from its m…

ClusteringTopological Data Analysis

Story Trees: Representing Documents using Topological Persistence

2022-06-01 · LREC 2022 6 · Pantea Haghighatkhah, Antske Fokkens, Pia Sommerauer, Bettina Speckmann 외

Topological Data Analysis (TDA) focuses on the inherent shape of (spatial) data. As such, it may provide useful methods to explore spatial representations of linguistic data (embeddings) which have become central in NLP.…

Topological Data Analysis

Exploring Dowker Homology for Sentence Similarity

2026-08-24 · Marius Huber, Juri Opitz arxiv

Dowker homology is a topological tool that may be used to analyze the relative position of two point clouds living in a common space. We investigate whether Dowker homology captures sentence similarity information by tre…

Point Clouds

Persistent Homology and Graphs Representation Learning

2021-02-25 · Mustafa Hajij, Ghada Zamzmi, Xuanting Cai

This article aims to study the topological invariant properties encoded in node graph representational embeddings by utilizing tools available in persistent homology. Specifically, given a node embedding representation a…

Representation Learning

Persistent Homology and Graphs Representation Learning

2021-03-08 · Anonymous

This article aims to study the topological invariant properties encoded in node graph representational embeddings by utilizing tools available in persistent homology. Specifically, given a node embedding representation a…

Representation Learning