A Model for Fine-Grained Alignment of Multilingual Texts

TL;DR

This paper introduces a predicate-argument structure-based model for fine-grained alignment of multilingual texts, effectively handling non-literal translations and bridging the gap between sentence and word alignment.

Contribution

It presents a novel alignment model that explicitly encodes non-literal translations using predicate-argument structures, enabling more precise multilingual text alignment.

Findings

Model effectively handles non-literal translations

Applied in English-German treebank project

Potential for extension to additional languages

Abstract

While alignment of texts on the sentential level is often seen as being too coarse, and word alignment as being too fine-grained, bi- or multilingual texts which are aligned on a level in-between are a useful resource for many purposes. Starting from a number of examples of non-literal translations, which tend to make alignment difficult, we describe an alignment model which copes with these cases by explicitly coding them. The model is based on predicate-argument structures and thus covers the middle ground between sentence and word alignment. The model is currently used in a recently initiated project of a parallel English-German treebank (FuSe), which can in principle be extended with additional languages.