Training the phrase table by force-aligning (FA) the training data with the reference translation has been shown to improve the phrasal translation quality while significantly reducing the phrase table size on medium ...
详细信息
ISBN:
(纸本)9781622765928
Training the phrase table by force-aligning (FA) the training data with the reference translation has been shown to improve the phrasal translation quality while significantly reducing the phrase table size on medium sized tasks. We apply this procedure to several large-scale tasks, with the primary goal of reducing model sizes without sacrificing translation quality. To deal with the noise in the automatically crawled parallel training data, we introduce on-demand word deletions, insertions, and backoffs to achieve over 99% successful alignment rate. We also add heuristics to avoid any increase in OOV rates. We are able to reduce already heavily pruned baseline phrase tables by more than 50% with little to no degradation in quality and occasionally slight improvement, without any increase in OOVs. We further introduce two global scaling factors for re-estimation of the phrase table via posterior phrase alignment probabilities and a modified absolute discounting method that can be applied to fractional counts.
Neural Network language models (NNLMs) have recently become an important complement to conventional n-gram language models (LMs) in speech-to-text systems. However, little is known about the behavior of NNLMs. The ana...
详细信息
Neural Network language models (NNLMs) have recently become an important complement to conventional n-gram language models (LMs) in speech-to-text systems. However, little is known about the behavior of NNLMs. The analysis presented in this paper aims to understand which types of events are better modeled by NNLMs as compared to n-gram LMs, in what cases improvements are most substantial and why this is the case. Such an analysis is important to take further benefit from NNLMs used in combination with conventional n-gram models. The analysis is carried out for different types of neural network (feed-forward and recurrent) LMs. The results showing for which type of events NNLMs provide better probability estimates are validated on two setups that are different in their size and the degree of data homogeneity.
This paper describes the statistical machine translation (SMT) systems developed at RWTH Aachen University for the translation task of the NAACL 2012 Seventh Workshop on Statistical Machine Translation (WMT 2012). We ...
详细信息
ISBN:
(纸本)9781622765928
This paper describes the statistical machine translation (SMT) systems developed at RWTH Aachen University for the translation task of the NAACL 2012 Seventh Workshop on Statistical Machine Translation (WMT 2012). We participated in the evaluation campaign for the French-English and German-English language pairs in both translation directions. Both hierarchical and phrase-based SMT systems are applied. A number of different techniques are evaluated, including an insertion model, different lexical smoothing methods, a discriminative reordering extension for the hierarchical system, reverse translation, and system combination. By application of these methods we achieve considerable improvements over the respective baseline systems.
On dedicated websites, people can upload videos and share it with the rest of the world. Currently these videos are categorized manually by the help of the user community. In this paper, we propose a combination of co...
详细信息
We present an analysis of music modeling and recognition techniques in the context of mobile music matching, substantially improving on the techniques presented in [1]. We accomplish this by adapting the features spec...
详细信息
We present an analysis of music modeling and recognition techniques in the context of mobile music matching, substantially improving on the techniques presented in [1]. We accomplish this by adapting the features specifically to this task, and by introducing new modeling techniques that enable using a corpus of noisy and channel-distorted data to improve mobile music recognition quality. We report the results of an extensive empirical investigation of the system's robustness under realistic channel effects and distortions. We show an improvement of recognition accuracy by explicit duration modeling of music phonemes and by integrating the expected noise environment into the training process. Finally, we propose the use of frame-to-phoneme alignment for high-level structure analysis of polyphonic music.
Log-linear models are a promising approach for speech recognition. Typically, log-linear models are trained according to a strictly convex criterion. Optimization algorithms are guaranteed to converge to the unique gl...
详细信息
In this paper, we investigate lexicon models for hierarchical phrase-based statistical machine translation. We study five types of lexicon models: a model which is extracted from word-aligned training data and-given t...
详细信息
Punctuation prediction is an important task in Spoken language Translation. The output of speech recognition systems does not typically contain punctuation marks. In this paper we analyze different methods for punctua...
详细信息
The increasing popularity of statistical machine translation (SMT) systems is introducing new domains of translation that need to be tackled. As many resources are already available, domain adaptation methods can be a...
详细信息
暂无评论