A Survey of Word Reordering in Statistical Machine Translation: Computational Models and Language Phenomena

TL;DR

This survey reviews the challenges and methods of word reordering in statistical machine translation, emphasizing the importance of linguistic phenomena and empirical analysis for improving translation quality across language pairs.

Contribution

It provides a comprehensive overview of reordering models in SMT, analyzes linguistic factors affecting reordering, and offers insights for selecting suitable models based on language-specific phenomena.

Findings

Certain linguistic facts can predict reordering behavior.

Different reordering models perform variably across language pairs.

Understanding language-specific phenomena improves SMT reordering strategies.

Abstract

Word reordering is one of the most difficult aspects of statistical machine translation (SMT), and an important factor of its quality and efficiency. Despite the vast amount of research published to date, the interest of the community in this problem has not decreased, and no single method appears to be strongly dominant across language pairs. Instead, the choice of the optimal approach for a new translation task still seems to be mostly driven by empirical trials. To orientate the reader in this vast and complex research area, we present a comprehensive survey of word reordering viewed as a statistical modeling challenge and as a natural language phenomenon. The survey describes in detail how word reordering is modeled within different string-based and tree-based SMT frameworks and as a stand-alone task, including systematic overviews of the literature in advanced reordering modeling. We then question why some approaches are more successful than others in different language pairs. We argue that, besides measuring the amount of reordering, it is important to understand which kinds of reordering occur in a given language pair. To this end, we conduct a qualitative analysis of word reordering phenomena in a diverse sample of language pairs, based on a large collection of linguistic knowledge. Empirical results in the SMT literature are shown to support the hypothesis that a few linguistic facts can be very useful to anticipate the reordering characteristics of a language pair and to select the SMT framework that best suits them.