Search for dissertations about: "Statistical machine translation"

Showing result 1 - 5 of 10 swedish dissertations containing the words Statistical machine translation.

2. 1. Translation as Linear Transduction : Models and Algorithms for Efficient Learning in Statistical Machine Translation

   Author : Markus Saers; Joakim Nivre; Anna Sågvall Hein; Dekai Wu; Kevin Knight; Uppsala universitet; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; linear transduction; linear transduction grammar; inversion transduction; zipper finite-state automaton; zipper finite-state transducer; formal language theory; formal transduction theory; translation; automatic translation; machine translation; statistical machine translation; Computational linguistics; Datorlingvistik; Language technology; Språkteknologi; Computational Linguistics; Datorlingvistik;

   Abstract : Automatic translation has seen tremendous progress in recent years, mainly thanks to statistical methods applied to large parallel corpora. Transductions represent a principled approach to modeling translation, but existing transduction classes are either not expressive enough to capture structural regularities between natural languages or too complex to support efficient statistical induction on a large scale. READ MORE

4. 2. Discourse in Statistical Machine Translation

   Author : Christian Hardmeier; Joakim Nivre; Jörg Tiedemann; Marcello Federico; Lluís Màrquez; Uppsala universitet; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; Statistical machine translation; Discourse-level machine translation; Document decoding; Local search; Pronominal anaphora; Pronoun translation; Neural networks; Computational Linguistics; Datorlingvistik;

   Abstract : This thesis addresses the technical and linguistic aspects of discourse-level processing in phrase-based statistical machine translation (SMT). Connected texts can have complex text-level linguistic dependencies across sentences that must be preserved in translation. However, the models and algorithms of SMT are pervaded by locality assumptions. READ MORE

5. 3. Compound Processing for Phrase-Based Statistical Machine Translation

   Author : Sara Stymne; Lars Ahrenberg; Joakim Nivre; Alexander Fraser; Linköpings universitet; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Machine translation; compounds; factored translation; statistical machine translation; computational linguistics; Computational linguistics; Datorlingvistik; Language technology; Språkteknologi; Computer science; Datavetenskap;

   Abstract : In this thesis I explore how compound processing can be used to improve phrase-based statistical machine translation (PBSMT) between English and German/Swedish. Both German and Swedish generally use closed compounds, which are written as one word without spaces or other indicators of word boundaries. READ MORE

6. 4. Understanding Neural Machine Translation : An investigation into linguistic phenomena and attention mechanisms

   Author : Gongbo Tang; Joakim Nivre; Rico Sennrich; Philipp Koehn; Uppsala universitet; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; Neural machine translation; Linguistic phenomena; Ambiguity; Long-range dependency; Morphology; Negation; Attention mechanisms; Interpretation; Computational Linguistics; Datorlingvistik;

   Abstract : In this thesis, I explore neural machine translation (NMT) models via targeted investigation of various linguistic phenomena and thorough exploration of the internal structure of NMT models, in particular the attention mechanism. With respect to linguistic phenomena, I explore the ability of NMT models to translate ambiguous words, to learn long-range dependencies, to learn morphology, and to translate negation—linguistic phenomena that have been challenging for the older paradigm of statistical machine translation. READ MORE

7. 5. Text Harmonization Strategies for Phrase-Based Statistical Machine Translation

   Author : Sara Stymne; Lars Ahrenberg; Joakim Nivre; Nizar Habash; Linköpings universitet; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; HUMANIORA; HUMANITIES; Statistical machine translation; text harmonization; compound words; definiteness; reordering; unknown words;

   Abstract : In this thesis I aim to improve phrase-based statistical machine translation (PBSMT) in a number of ways by the use of text harmonization strategies. PBSMT systems are built by training statistical models on large corpora of human translations. This architecture generally performs well for languages with similar structure. READ MORE