Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Doelstelling: Deze scriptie heeft als doel een vergelijking te maken van twee benaderingen van automatische vertaling. Als voorbeeld van regelgebaseerde automatische vertaling kozen we Systran en Google Translate als voorbeeld van statistische automatische vertaling. Meer specifiek vergeleken we de prestaties van deze systemen voor het Engels en het Russisch. Middelen of methode: Deze twee vertaalsystemen werden getest aan de hand van een specifieke testsuite waar zeven moeilijke punten centraal staan. Door korte zinnetjes met deze moeilijke punten te laten vertalen door beide systemen, zowel voor Engels-Russisch als Russisch-Engels konden we achterhalen welke systemen beter overweg kunnen met welke moeilijkheden. Daarna lieten we ook nog een algemene journalistieke tekst vertalen om te zien hoe deze moeilijkheden aangepakt worden. Resultaten: Het is niet mogelijk om één van beide systeem als het 'beste systeem' uit te roepen. Beide maken veel fouten.Het is wel zo dat het ene systeem minder fouten maakt tegen bepaalde moeilijkheden dan het ander systeem en omgekeerd. Afhankelijk van de categorie presteert Google Translate beter dan Systran, maar in anderecategorieën maakt Systran dan toch minder fouten.

English. --- Google Translate. --- Machine translation. --- Rule-based machine translation. --- Russian. --- Statistical machine translation. --- Systran.

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Preface -- Acknowledgments -- 1. Introduction -- Applications -- Further readings -- 2. Basic concepts and terminology -- Bitext and alignment -- Alignment and segmentation -- Alignment spaces and constraints -- Correlations and cues -- Alignment models and search algorithms -- Evaluation of bitext alignment -- Summary and further reading -- 3. Building parallel corpora -- Document alignment -- Mining the web -- Extracting parallel data from comparable corpora -- Summary and further reading -- 4. Sentence alignment -- Length-based approaches -- Lexical matching approaches -- Combined and resource-specific techniques -- Summary and further reading -- 5. Word alignment -- Generative alignment models -- Constraints and heuristics -- Discriminative alignment models -- Translation spotting and bilingual lexicon induction -- Summary and further reading -- 6. Phrase and tree alignment -- Parallel treebanks and tree alignment -- Hierarchical alignment and transduction grammars -- Summary and further reading -- 7. Concluding remarks -- Final recommendations -- A. Resources & tools -- Bibliography -- Author's biography. This book provides an overview of various techniques for the alignment of bitexts. It describes general concepts and strategies that can be applied to map corresponding parts in parallel documents on various levels of granularity. Bitexts are valuable linguistic resources for many different research fields and practical applications. The most predominant application is machine translation, in particular, statistical machine translation. However, there are various other threads that can be followed which may be supported by the rich linguistic knowledge implicitly stored in parallel resources. Bitexts have been explored in lexicography, word sense disambiguation, terminology extraction, computer-aided language learning and translation studies to name just a few. The book covers the essential tasks that have to be carried out when building parallel corpora starting from the collection of translated documents up to sub-sentential alignments. In particular, it describes various approaches to document alignment, sentence alignment, word alignment and tree structure alignment. It also includes a list of resources and a comprehensive review of the literature on alignment techniques.

Machine translating. --- Computational linguistics. --- Bitexts. --- Sentence alignment. --- Languages & Literatures --- Philology & Linguistics --- Natural language processing (Computer science) --- NLP (Computer science) --- Automatic translating --- Computer translating --- Electronic translating --- Mechanical translating --- Alignment --- Bitexts --- Parallel corpora --- Sentence alignment --- Word alignment --- Tree alignment --- Statistical machine translation --- Transduction grammars --- Text mining --- Lexicon induction --- Artificial intelligence --- Electronic data processing --- Human-computer interaction --- Semantic computing --- Algorithms --- Applied linguistics --- Natural language generation (Computer science) --- Information theory --- Translating and interpreting --- Cross-language information retrieval --- Translating machines --- 681.3*I27 --- 800:311 --- 800:311 Kwantitatieve linguistiek. Computerlinguistiek --- Kwantitatieve linguistiek. Computerlinguistiek --- 681.3*I27 Natural language processing: language generation; language models; language parsing and understanding; machine translation; speech recognition and under-standing; text analysis (Artificial intelligence) --- Natural language processing: language generation; language models; language parsing and understanding; machine translation; speech recognition and under-standing; text analysis (Artificial intelligence) --- Automatic language processing --- Language and languages --- Language data processing --- Linguistics --- Natural language processing (Linguistics) --- Mathematical linguistics --- Multilingual computing --- Data processing