Dynamic Boundary Time Warping for Sub-sequence Matching with Few Examples

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Borchmann, Łukasz, Jurkiewicz, Dawid, Graliński, Filip, Górecki, Tomasz
Format: Preprint
Veröffentlicht: 2020
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913487063613440
author Borchmann, Łukasz
Jurkiewicz, Dawid
Graliński, Filip
Górecki, Tomasz
author_facet Borchmann, Łukasz
Jurkiewicz, Dawid
Graliński, Filip
Górecki, Tomasz
contents The paper presents a novel method of finding a fragment in a long temporal sequence similar to the set of shorter sequences. We are the first to propose an algorithm for such a search that does not rely on computing the average sequence from query examples. Instead, we use query examples as is, utilizing all of them simultaneously. The introduced method based on the Dynamic Time Warping (DTW) technique is suited explicitly for few-shot query-by-example retrieval tasks. We evaluate it on two different few-shot problems from the field of Natural Language Processing. The results show it either outperforms baselines and previous approaches or achieves comparable results when a low number of examples is available.
format Preprint
id arxiv_https___arxiv_org_abs_2010_14464
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Dynamic Boundary Time Warping for Sub-sequence Matching with Few Examples
Borchmann, Łukasz
Jurkiewicz, Dawid
Graliński, Filip
Górecki, Tomasz
Data Structures and Algorithms
Computation and Language
Information Retrieval
The paper presents a novel method of finding a fragment in a long temporal sequence similar to the set of shorter sequences. We are the first to propose an algorithm for such a search that does not rely on computing the average sequence from query examples. Instead, we use query examples as is, utilizing all of them simultaneously. The introduced method based on the Dynamic Time Warping (DTW) technique is suited explicitly for few-shot query-by-example retrieval tasks. We evaluate it on two different few-shot problems from the field of Natural Language Processing. The results show it either outperforms baselines and previous approaches or achieves comparable results when a low number of examples is available.
title Dynamic Boundary Time Warping for Sub-sequence Matching with Few Examples
topic Data Structures and Algorithms
Computation and Language
Information Retrieval
url https://arxiv.org/abs/2010.14464