A swarm-inspired re-ranker system for statistical machine translation. (January 2015)

• Record Type: Journal Article
• Authors: Farzi, Saeed; Faili, Heshaam
• Is Part Of: Computer speech & language. Volume 29(2015)
• Page Start: 45
• Page End: 62
• Publication Date: 2015-01
• Subjects: Re-ranking system -- Quantum-behaved particle swarm optimization -- Perceptron -- BLEU; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2014.07.002
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: We design and implement a novel reranker system for statistical machine translation, which it is used a swarm algorithm. We introduce sort of new features, which they can be computed easily from n-best list generated by SMT. We examine our system in English–Persian dataset. Abstract: Recently, re-ranking algorithms have been successfully applied on statistical machine translation systems. Due to the errors in the hypothesis alignment and varying word order between the source and target sentences and also the lack of sufficient resources such as parallel corpora, decoding may result in ungrammatical or non-fluent outputs. This paper proposes a re-ranking system based on swarm algorithms, which makes the use of sophisticated non-syntactical features to re-rank the n-best translation candidates. We introduce plenty of easy-computed non-syntactical features to deal with SMT system errors plus the quantum-behaved particle swarm optimization (QPSO) algorithm to adjust the weights of features. We have evaluated the proposed approach on 2 translation tasks in different language pairs (Persian → English and German → English) and genres (news and novel books). In comparison with PSO-, GA-, Perceptron- and averaged Perceptron-style re-ranking systems, the experimental study demonstrates the superiority of the proposed system in terms of translation quality on both translation tasks. In addition, the impacts of the proposed features on the translation quality have been analyzed, and the most positive ones have been recognized. At the end, the impact of the n-best list size on the proposed system is investigated.