Improving the Automatic Segmentation of Subtitles through Conditional Random Field

Authors: Aitor Álvarez Muniain Carlos-D. Martínez-Hinarejos Haritz Arzelus Irazusta Marina Balenciaga Arantza del Pozo Echezarreta

Date: 01.04.2017

Speech Communication


PDF

Abstract

Automatic segmentation of subtitles is a novel research field which has not been studied extensively to date. However, quality automatic subtitling is a real need for broadcasters which seek for automatic solutions given the demanding European audiovisual legislation. In this article, a method based on Conditional Random Field is presented to deal with the automatic subtitling segmentation. This is a continuation of a previous work in the field, which proposed a method based on Support Vector Machine classifi er to generate possible candidates for breaks. For this study, two corpora in Basque and Spanish were used for experiments, and the performance of the current method was tested and compared with the previous solution and two rule-based systems through several evaluation metrics. Finally, an experiment with human evaluators was carried out with the aim of measuring the productivity gain in post-editing automatic subtitles generated with the new method presented.

BIB_text

@Article {
title = {Improving the Automatic Segmentation of Subtitles through Conditional Random Field},
journal = {Speech Communication},
pages = {83.-95},
volume = {88},
keywds = {

automatic subtitling, subtitle segmentation, pattern recognition, machine learning


}
abstract = {

Automatic segmentation of subtitles is a novel research field which has not been studied extensively to date. However, quality automatic subtitling is a real need for broadcasters which seek for automatic solutions given the demanding European audiovisual legislation. In this article, a method based on Conditional Random Field is presented to deal with the automatic subtitling segmentation. This is a continuation of a previous work in the field, which proposed a method based on Support Vector Machine classifi er to generate possible candidates for breaks. For this study, two corpora in Basque and Spanish were used for experiments, and the performance of the current method was tested and compared with the previous solution and two rule-based systems through several evaluation metrics. Finally, an experiment with human evaluators was carried out with the aim of measuring the productivity gain in post-editing automatic subtitles generated with the new method presented.


}
isi = {1},
doi = {10.1016/j.specom.2017.01.010},
date = {2017-04-01},
year = {2017},
}
Vicomtech

Parque Científico y Tecnológico de Gipuzkoa,
Paseo Mikeletegi 57,
20009 Donostia / San Sebastián (Spain)

+(34) 943 309 230

close overlay