In this paper we describe the components of our statistical machine translation system used for the spoken language translation evaluation campaign. This system is based on phrase-to-phrase translations extracted from a bilingual corpus. A new phrase alignment approaches will be introduced, which finds the target phrase by optimizing the overall word-to-word alignment for the sentence pair unde...

Phrase chunking remains an important natural language processing (NLP) technique for intermediate syntactic processing. This paper describes the development of protocols, annotated phrase chunking data sets and automatic phrase chunkers for ten South African languages. Various problems with adapting the existing annotation protocols of English are discussed as well as an overview of the annotat...

Phrase-based statistical models constitute one of the most competitive pattern-recognition approaches to machine translation. In this case, the source sentence is fragmented into phrases, then, each phrase is translated by using a stochastic dictionary. One shortcoming of this phrase-based model is that it does not have an adequate generalization capability. If a sequence of words has not been ...

This paper describes the 2010 phrase-based statistical machine translation system developed at the TALP Research Center of the UPC in cooperation with BMIC and VMU. In phrase-based SMT, the phrase table is the main tool in translation. It is created extracting phrases from an aligned parallel corpus and then computing translation model scores with them. Performing a collocation segmentation ove...

The article analyses violations of the Obligatory Contour Principle (OCP) above word level in Tswana, a Southern Bantu language, by investigating realization adjacent lexical high tones across boundaries. results show that boundaries downstep (i.e. lowering second series tones) only takes place within phonological phrase. A phrase break blocks downstep, even when necessary tonal configuration i...

Phrase alignment is a crucial step in phrase-based statistical machine translation. We explore a way of improving phrase alignment by adding syntactic information in the form of chunks as soft constraints guided by an in-depth and detailed analysis on a hand-aligned data set. We extend a probabilistic phrase alignment model that extracts phrase pairs by optimizing phrase pair boundaries over th...

Support Verb Constructions (SVCs) pose interesting problems because of their mixed nature, with idiomatic properties in the sense that they do not seem to comply with general rules, and yet displaying a large number of regularities. The problems we will be concerned with in this paper are the following: • What is event structure, and how is expressed in SVCs? • What verbs may function as suppor...

Given a pair of source and target language sentences which are translations of each other with known word alignments between them, we extract bilingual phrase-level segmentations of such a pair. This is done by identifying two appropriate measures that assess the quality of phrase segments, one on the monolingual level for both language sides, and one on the bilingual level. The monolingual mea...

The performance of phrase-based statistical machine translation (SMT) systems is crucially dependent on the quality of the extracted phrase pairs, which is in turn a function of word alignment quality. Data sparsity, an inherent problem in SMT even with large training corpora, often has an adverse impact on the reliability of the extracted phrase translation pairs. In this paper, we present a n...

Abstract This article is intended as the first of a series papers designing an electronic linguistic resource made up three modules: (1) phrase-based active dictionary thought attempt to implement John Sinclair’s vision “ultimate dictionary”; (2) grammar / construction describing not only morphologic and syntactic rules language but also its systematic (semantic) alternations derivations genera...