Title Generation for Machine-Translated Documents
Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence. Pages 1229-1233.
Abstract
In this paper, we present and compare automatically generated titles for machine-translated documents using several different statistics-based methods. A Naïve Bayesian, a K-Nearest Neighbour, a TF-IDF and an iterative Expectation-Maximization method for title generation were applied to 1000 original English news documents and again to the same documents translated from English into Portuguese, French or German and back to English using SYSTRAN. The AutoSummarization function of Microsoft Word was used as a base line. Results on several metrics show that the statistics-based methods of title generation for machine-translated documents are fairly language independent and title generation is possible at a level approaching the accuracy of titles generated for the original English documents.
@inproceedings{ijcai2001p162,
title = {Title Generation for Machine-Translated Documents},
author = {Jin, Rong and Hauptmann, Alexander G.},
booktitle = {Proceedings of the Seventeenth International Joint Conference on
Artificial Intelligence, {IJCAI-01}},
publisher = {International Joint Conferences on Artificial Intelligence},
pages = {1229--1233},
year = {2001},
url = {https://ijcai.org/proceedings/2001/162},
}
TY - CPAPER TI - Title Generation for Machine-Translated Documents AU - Jin, Rong AU - Hauptmann, Alexander G. T2 - Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence, IJCAI-01 PB - International Joint Conferences on Artificial Intelligence PY - 2001 SP - 1229 EP - 1233 UR - https://ijcai.org/proceedings/2001/162 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
