Story Trees: Representing Documents using Topological Persistence
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. In this paper we aim to introduce TDA to researchers in language technology. We use TDA to represent document structure as so-called story trees. Story trees are hierarchical representations created from semantic vector representations of sentences via persistent homology. They can be used to identify and clearly visualize prominent components of a story line. We showcase their potential by using story trees to create extractive summaries for news stories.
Code (0)
등록된 구현이 없습니다.
Tasks
Topological Data AnalysisSimilar Papers 제목 키워드 기반
Topological Analysis of Ensembles of Hydrodynamic Turbulent Flows -- An Experimental Study
This application paper presents a comprehensive experimental evaluation of the suitability of Topological Data Analysis (TDA) for the quantitative comparison of turbulent flows. Specifically, our study documents the usag…
Topological Data AnalysisPersistence B-Spline Grids: Stable Vector Representation of Persistence Diagrams Based on Data Fitting
Many attempts have been made in recent decades to integrate machine learning (ML) and topological data analysis. A prominent problem in applying persistent homology to ML tasks is finding a vector representation of a per…
Topological Data AnalysisTopological Quality of Subsets via Persistence Matching Diagrams
Data quality is crucial for the successful training, generalization and performance of machine learning models. We propose to measure the quality of a subset concerning the dataset it represents, using topological data a…
Topological Data AnalysisA Note on Community Trees in Networks
We introduce the concept of community trees that summarizes topological structures within a network. A community tree is a tree structure representing clique communities from the clique percolation method (CPM). The comm…
Zero-shot Active Learning with Topological Clustering for Multiclass Classification
We present a novel approach for zero-shot active learning for multi-class classification based on a clustering technique, called ToMATo, which is guided by topological persistence. Our objective is to identify effective …
Active LearningClusteringMulti-class Classification