A stylometric study and assessment of machine translators

Authors:
V. Suresh;Avanthi Krishnamurthy;Rama Badrinath;C. E. Veni Madhavan
Affiliations:
Department of Computer Science and Automation, Indian Institute of Science, Bangalore, India;Department of Computer Science and Automation, Indian Institute of Science, Bangalore, India;Department of Computer Science and Automation, Indian Institute of Science, Bangalore, India;Department of Computer Science and Automation, Indian Institute of Science, Bangalore, India
Venue:
IDA'11 Proceedings of the 10th international conference on Advances in intelligent data analysis X
Year:
2011

Citing 7
Cited 0

Latent dirichlet allocation

The Journal of Machine Learning Research
The mathematics of statistical machine translation: parameter estimation

Computational Linguistics - Special issue on using large corpora: II
BLEU: a method for automatic evaluation of machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Automatic evaluation of machine translation quality using n-gram co-occurrence statistics

HLT '02 Proceedings of the second international conference on Human Language Technology Research
Meteor: an automatic metric for MT evaluation with high levels of correlation with human judgments

StatMT '07 Proceedings of the Second Workshop on Statistical Machine Translation
Stopword Graphs and Authorship Attribution in Text Corpora

ICSC '09 Proceedings of the 2009 IEEE International Conference on Semantic Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work we present a statistical approach inspired by stylometry -measurement of author style- to study the characteristics of machine translators. Our approach quantifies the style of a translator in terms of the properties derived from the distribution of stopwords in its output - a standard approach in modern stylometry. Our study enables us to match translated text to the source machine translator that generated them. Also, the stylometric closeness of human generated text to that generated by machine translators provides handles to assess the quality of machine translators.