Aligning parallell terms in a parallell corpus can be done by aligning all words and phrases in the corpus and then performing term extraction on the aligned set of word pairs. Alternatively, term extraction in the source and target text can be made separately and then the resulting term candidates can be aligned, forming aligned parallell terms. This thesis describes an implementation of a word aligner that is applied on extracted term candidates in both the source and the target texts. The term aligner uses statistical measures, the tool Giza++ and heuristics in the search for alignments. The evaluation reveals that the best results are obtained when the term alignment relies heavily on the Giza++ tool and Levenshtein heuristic.

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

Idag finns det m˚anga system f¨or att bed¨oma och tolka ¨overs¨attningar av texter. Det finns system som l¨ankar delar av en k¨alltext och en ¨overs¨attning, det finns en ¨aven tekniker f¨or att bed¨oma ¨overs¨attningar f¨or ge ett m˚att p˚a hur bra de ¨ar. Ett exempel p˚a en s˚adan teknik ¨ar Token Equivalence Method(TEM). Det finns dock f˚a program, om n˚agra, som utnyttjar b˚ade l¨ankning och bed¨omning p˚a ett s˚adant s¨att att de skulle kunna vara anv¨andbara vid till exempel spr˚akutbildningar. I detta arbete utvecklas just ett s˚adant program. Programmet som skapats kan segmentera och l¨anka parallella texter mot varandra helt automatiskt via inkopplade system. F¨or att ¨oka anv¨andarv¨anligheten s˚a visualiserar programmet ¨aven l¨ankningen och till˚ater redigering av b˚ade segmentering och l¨ankning. L¨ankningen utnyttjas sedan f¨or att r¨akna ut och visa delar av TEM f¨or att ge ett m˚att p˚a ¨overs¨attningens kvalit´e.

This Master thesis deals with machine translation from Czech to Slovak. The first chapter motivates the work, the second discusses various approaches to machine translation and the third details evaluation of the methods. Chapter 4 introduces the design and implementation of my system, paying a special attention to a new parallel corpus that has been created. Chapter 5 summarizes testing and evaluation of the developed system.

<p>This project evaluates two different systems that generate wordalignments on English-Swedish data. The systems to be used are the Giza++ system, that may generate a variety of statistical translation models, and I*Trix system developed at IDA/NLPLab that generates word pairs with frequencies. </p><p>The file formats of these two systems, the way of running them and the differences of the two systems are addressed in this paper. Evaluation in this project considers a variety of parameters such as corpus size, characteristics of the corpus, the effect of linguistic knowledge, etc. At the end of this paper, the conclusions of the two systems evaluation are presented. In general, Giza++ is better applying on big corpora while I*Trix is better for small corpora. Especially for corpora with high statistical ratio or special resource, I*Trix has a better performance.</p>

This project evaluates two different systems that generate wordalignments on English-Swedish data. The systems to be used are the Giza++ system, that may generate a variety of statistical translation models, and I*Trix system developed at IDA/NLPLab that generates word pairs with frequencies. The file formats of these two systems, the way of running them and the differences of the two systems are addressed in this paper. Evaluation in this project considers a variety of parameters such as corpus size, characteristics of the corpus, the effect of linguistic knowledge, etc. At the end of this paper, the conclusions of the two systems evaluation are presented. In general, Giza++ is better applying on big corpora while I*Trix is better for small corpora. Especially for corpora with high statistical ratio or special resource, I*Trix has a better performance.

Aim of this thesis is to implement system for translation words from source language into the target language with pair input texts. There are descriptions  of terms and methods used in machine translation and machine build dictionary. The thesis also contains a concept and specification of each part created system including final evaluation. There is analysed options which make extension of existing dictionatry.

Tato diplomová práce popisuje principy statistického strojového překladu a demonstruje, jak sestavit systém pro statistický strojový překlad Moses. V přípravné fázi jsou prozkoumány volně dostupné bilingvní česko-anglické korpusy. Empirická analýza časové náročnosti vícevláknových nástrojů pro zarovnání slov demonstruje, že MGIZA++ může dosáhnout až pětinásobného zrychlení, zatímco PGIZA++ až osminásobného zrychlení (v porovnání s GIZA++). Jsou otestovány tři způsoby morfologického pre-processingu českých trénovacích dat za použití jednoduchých nefaktorových modelů. Zatímco jednoduchá lemmatizace může snížit BLEU, sofistikovanější přístupy většinou BLEU zvyšují. Positivní efekty morfologického pre-processingu se vytrácejí s růstem velikosti korpusu. Vztah mezi dalšími charakteristikami korpusu (velikost, žánr, další data) a výsledným BLEU je empiricky měřen. Koncový systém je natrénován na korpusu CzEng 0.9 a vyhodnocen na testovacím vzorku z workshopu WMT 2010.