Generative Training and Smoothing of Hierarchical Phrase-Based Translation Models

Peitz, Stephan; Ney, Hermann (Thesis advisor); Allauzen, Alexandre (Thesis advisor)

Aachen (2017)
Dissertation / PhD Thesis

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.

Institutions

  • Department of Computer Science [120000]
  • Chair of Computer Science 6 (Machine Learning and Reasoning) [122010]