h1

% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@PHDTHESIS{Peitz:709157,
      author       = {Peitz, Stephan},
      othercontributors = {Ney, Hermann and Allauzen, Alexandre},
      title        = {{G}enerative {T}raining and {S}moothing of {H}ierarchical
                      {P}hrase-{B}ased {T}ranslation {M}odels},
      school       = {RWTH Aachen University},
      type         = {Dissertation},
      address      = {Aachen},
      reportid     = {RWTH-2017-09742},
      pages        = {1 Online-Ressource (xi, 111 Seiten) : Illustrationen,
                      Diagramme},
      year         = {2017},
      note         = {Veröffentlicht auf dem Publikationsserver der RWTH Aachen
                      University; Dissertation, RWTH Aachen University, 2017},
      abstract     = {Hierarchical phrase-based translation is a common machine
                      translation approach for translating between languages with
                      signicantly dierent word order. The focus of the first part
                      of this thesis is set on smoothing and training of the
                      translation models used in hierarchical translation.
                      Additionally, we present an improved implementation of the
                      search algorithm and show that our implementation is
                      competitive compared to other state-of-the-art hierarchical
                      phrase-based translationengines. Within the second part of
                      this work, we apply hierarchical phrase-basedtranslation in
                      the context of spoken language translation. In the
                      state-of-the-art hierarchical translation model extraction
                      process, translation rules and their corresponding
                      translation probabilities are obtained from word-aligned
                      training data by applying simple heuristics. A common issue
                      is that even if a large set of training data is provided,
                      the resulting translation model may suffer from data
                      sparseness. Smoothing is an approach to remedy this problem
                      and is well-known from othernatural language processing
                      tasks (e.g. languagemodeling). The goal of smoothing applied
                      in the scope of machine translation is to model rarely seen
                      translation rules better. In this thesis, we investigate and
                      compare different smoothing techniques for hierarchical
                      phrase-based translation.Furthermore, the extraction and
                      translation processes are two separated steps. Therefore,
                      the extraction does not take into account whether the
                      obtained translation rules are actually needed in the
                      translation process. To learn whether a translation rule is
                      relevant for the translation process, we pursue the approach
                      of force-decoding the training data. Given a sentence pair
                      of the training data, the translation of the source sentence
                      is constrained to produce the corresponding targetsentence.
                      The applied translation rules are then determined and the
                      corresponding translation probabilities re-estimated. In
                      order to be able to translate a large set of training data,
                      an efficient and fast framework is needed. In this work, we
                      introduce such a framework for re-estimating hierarchical
                      translation models. This approach enables us to obtain
                      smaller translation models while simultaneously improving
                      the translation quality. We further compare our proposed
                      schemewith another state-of-the-art translation model
                      training approach, namely discriminative training, on a
                      large-scale Chinese-to-English translation task.Spoken
                      language translation is the task of translating
                      automatically transcribed speech. Since most automatic
                      speech recognition systems provide transcriptions without
                      punctuation marks and case information, this information has
                      to be re-introduced before the actual translation takes
                      place. In this work, we show that performing punctuation
                      prediction and re-casing by applying a machinetranslation
                      system helps to improve the translation quality. In
                      particular, we propose to apply hierarchical translation
                      rather than phrase-based translation for this task. Finally,
                      experiments were conducted on a large-scale
                      English-to-French spoken language translation task.All
                      methods described in this thesis have been made freely
                      available to the research community as they were integrated
                      into the open-source translation toolkit Jane.},
      cin          = {120000 / 122010},
      ddc          = {004},
      cid          = {$I:(DE-82)120000_20140620$ / $I:(DE-82)122010_20140620$},
      typ          = {PUB:(DE-HGF)11},
      doi          = {10.18154/RWTH-2017-09742},
      url          = {https://publications.rwth-aachen.de/record/709157},
}