Linguistic Features of Genre and Method Variation in Translation: A Computational Perspective

TL;DR

This study employs text classification with linguistically motivated features to analyze genre and method variation in English-German translation, revealing key linguistic differences through a Bayesian classifier approach.

Contribution

It introduces a computational method using part-of-speech n-grams and Bayesian classification to distinguish translation genres and methods, providing detailed feature analysis.

Findings

Successful classification of translation genres and methods

Identification of key linguistic features differentiating genres

Insights into linguistic variation in translation

Abstract

In this paper we describe the use of text classification methods to investigate genre and method variation in an English - German translation corpus. For this purpose we use linguistically motivated features representing texts using a combination of part-of-speech tags arranged in bigrams, trigrams, and 4-grams. The classification method used in this paper is a Bayesian classifier with Laplace smoothing. We use the output of the classifiers to carry out an extensive feature analysis on the main difference between genres and methods of translation.