Syntactic reordering integrated with phrase-based SMT

Abstract

We present a novel approach to word reordering which successfully integrates syntactic structural knowledge with phrase-based SMT. This is done by constructing a lattice of alternatives based on automatically learned probabilistic syntactic rules. In decoding, the alternatives are scored based on the output word order, not the order of the input. Unlike previous approaches, this makes it possible to successfully integrate syntactic reordering with phrase-based SMT. On an EnglishDanish task, we achieve an absolute improvement in translation quality of 1.1 % BLEU. Manual evaluation supports the claim that the present approach is significantly superior to previous approaches.

Knowledge representation of Urdu text using predicate logic

“…It provides machine translation with robustness in word selection and local words reordering. A significant improvement in English-Danish machine translation has been achieved [8]. The phrase level representation of source language, converting the source language phrases into target language phrases and reordering the target language phrases generate fluent target output [9].…”

A POS-Based Preordering Approach for English-to-Arabic Statistical Machine Translation

“…They used a source-reordering lattice instead of a single best reordering, and a reordering source language model as an additional feature to score each path in the lattice. Elming [12] presented a preordering approach for Englishto-Danish translation. His proposed approach automatically learns probabilistic rules from a parallel corpus.…”

Computational Linguistics and Intelligent Text Processing

“…The technique was produced firstly by [Elm08] but on a close language pair English-Danish. They proved that the technique was viable for distant language pair like English-Arabic.…”