检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Robin Schmitt Albert Zeyer Mohammad Zeineldeen Ralf Schlűter Hermann Ney Computer Science Department Human Language Technology and Pattern Recognition RWTH Aachen University Aachen Germany AppTek GmbH Aachen Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

We sometimes observe monotonically decreasing cross-attention weights in our Conformer-based global attention-based encoder-decoder (AED) models, negatively affecting performance compared to monotonically increasing attention weights. Further investigation shows that the Conformer encoder reverses the sequence in the time dimension. We analyze the initial behavior of the decoder cross-attention mechanism and find that it encourages the Conformer encoder self-attention to build a connection between the initial frames and all other informative frames. Furthermore, we show that, at some point in training, the self-attention module of the Conformer starts dominating the output over the preceding feed-forward module, which then only allows the reversed information to pass through. We propose methods and ideas of how this flipping can be avoided and investigate a novel method to obtain label-frame-position alignments by using the gradients of the label log probabilities w.r.t. the encoder input frames.

关键词： Training Signal processing Acoustics Decoding Speech processing

来源：评论

学校读者我要写书评

暂无评论

Spoken language processing techniques for sign language recognition and translation

引用

technology and Disability 2008年第2期20卷 121-133页

作者： Dreuw, Philippe Stein, Daniel Deselaers, Thomas Rybach, David Zahedi, Morteza Bungeroth, Jan Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department 6 RWTH Aachen University Aachen Germany

We present an approach to automatically recognize sign language and translate it into a spoken language. A system to address these tasks is created based on state-of-the-art techniques from statistical machine translation, speech recognition, and image processing research. Such a system is necessary for communication between deaf and hearing people. The communication is otherwise nearly impossible due to missing sign language skills on the hearing side, and the low reading and writing skills on the deaf side. As opposed to most current approaches, which focus on the recognition of isolated signs only, we present a system that recognizes complete sentences in sign language. Similar to speech recognition, we have to deal with temporal sequences. Instead of the acoustic signal in speech recognition, we process a video signal as input. Therefore, we use a speech recognition system to obtain a textual representation of the signed sentences. This intermediate representation is then fed into a statistical machine translation system to create a translation into a spoken language. To achieve good results, some particularities of sign languages are considered in both systems. We use a publicly available corpus to show the performance of the proposed system and report very promising results. © 2008 IOS Press. All rights reserved.

关键词： computer input-output equipment SIGN language SYMBOLIC communication MEANS of communication for deaf people SPEECH perception AUTOMATIC speech recognition

来源：评论

学校读者我要写书评

暂无评论

The RWTH 2010 Quaero ASR evaluation system for English, French, and German

The RWTH 2010 Quaero ASR evaluation system for English, Fren...

引用

36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011

作者： Sundermeyer, M. Nussbaum-Thom, M. Wiesler, S. Plahl, C. El-Desoky Mousa, A. Hahn, S. Nolden, D. Schlüter, R. Ney, H. Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Germany

ISBN: (纸本)9781457705397

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Modeling Punctuation Prediction as Machine Translation 8

Modeling Punctuation Prediction as Machine Translation

引用

8th International Workshop on Spoken language Translation, IWSLT 2011

作者： Peitz, Stephan Freitag, Markus Mauser, Arne Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

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 punctuation prediction and show improvements in the quality of the final translation output. In our experiments we compare the different approaches and show improvements of up to 0.8 BLEU points on the IWSLT 2011 English French Speech Translation of Talks task using a translation system to translate from unpunctuated to punctuated text instead of a language model based punctuation prediction method. Furthermore, we do a system combination of the hypotheses of all our different approaches and get an additional improvement of 0.4 points in BLEU. © IWSLT 2011. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Translation model based weighting for phrase extraction 17

Translation model based weighting for phrase extraction

引用

17th Annual Conference of the European Association for Machine Translation, EAMT 2014

作者： Mansour, Saab Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

ISBN: (纸本)9789535537533

Domain adaptation for statistical machine translation is the task of altering general models to improve performance on the test domain. In this work, we suggest several novel weighting schemes based on translation models for adapted phrase extraction. To calculate the weights, we first phrase align the general bilingual training data, then, using domain specific translation models, the aligned data is scored and weights are defined over these scores. Experiments are performed on two translation tasks, German-to-English and Arabic-to-English translation with lectures as the target domain. Different weighting schemes based on translation models are compared, and significant improvements over automatic translation quality are reported. In addition, we compare our work to previous methods for adaptation and show significant gains. © 2014 The authors.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

MorphTagger: HMM-Based Arabic Segmentation for Statistical Machine Translation 7

MorphTagger: HMM-Based Arabic Segmentation for Statistical M...

引用

7th International Workshop on Spoken language Translation, IWSLT 2010

作者： Mansour, Saab Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

In this paper, we investigate different methodologies of Arabic segmentation for statistical machine translation by comparing a rule-based segmenter to different statistically-based segmenters. We also present a new method for segmentation that serves the need for a real-time translation system without impairing the translation accuracy. © IWSLT 2010. All rights reserved.

关键词： computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

A Simple and Effective Weighted Phrase Extraction for Machine Translation Adaptation 9

A Simple and Effective Weighted Phrase Extraction for Machin...

引用

9th International Workshop on Spoken language Translation, IWSLT 2012

作者： Mansour, Saab Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

The task of domain-adaptation attempts to exploit data mainly drawn from one domain (e.g. news) to maximize the performance on the test domain (e.g. weblogs). In previous work, weighting the training instances was used for filtering dissimilar data. We extend this by incorporating the weights directly into the standard phrase training procedure of statistical machine translation (SMT). This allows the SMT system to make the decision whether to use a phrase translation pair or not, a more methodological way than discarding phrase pairs completely when using filtering. Furthermore, we suggest a combined filtering and weighting procedure to achieve better results while reducing the phrase table size. The proposed methods are evaluated in the context of Arabic-to-English translation on various conditions, where significant improvements are reported when using the suggested weighted phrase training. The weighting method also improves over filtering, and the combined filtering and weighting is better than a standalone filtering method. Finally, we experiment with mixture modeling, where additional improvements are reported when using weighted phrase extraction over a variety of baselines. © IWSLT 2012. All rights reserved.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Improved decipherment of homophonic ciphers

Improved decipherment of homophonic ciphers

引用

2014 Conference on Empirical Methods in Natural language Processing, EMNLP 2014

作者： Nuhn, Malte Schamper, Julian Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

ISBN: (纸本)9781937284961

In this paper, we present two improvements to the beam search approach for solving homophonic substitution ciphers presented in Nuhn et al. (2013): An improved rest cost estimation together with an optimized strategy for obtaining the order in which the symbols of the cipher are deciphered reduces the beam size needed to successfully decipher the Zodiac-408 cipher from several million down to less than one hundred: The search effort is reduced from several hours of computation time to just a few seconds on a single CPU. These improvements allow us to successfully decipher the second part of the famous Beale cipher (see (Ward et al., 1885) and e.g. (King, 1993)): Having 182 different cipher symbols while having a length of just 762 symbols, the decipherment is way more challenging than the decipherment of the previously deciphered Zodiac- 408 cipher (length 408, 54 different symbols). To the best of our knowledge, this cipher has not been deciphered automatically before. © 2014 Association for Computational Linguistics.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Combining Translation and language Model Scoring for Domain-Specific Data Filtering 8

Combining Translation and Language Model Scoring for Domain-...

引用

8th International Workshop on Spoken language Translation, IWSLT 2011

作者： Mansour, Saab Wuebker, Joern Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

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 applied to utilize these recourses in the most beneficial way for the new domain. We explore adaptation via filtering, using the cross-entropy scores to discard irrelevant sentences. We focus on filtering for two important components of an SMT system, namely the language model (LM) and the translation model (TM). Previous work has already applied LM cross-entropy based scoring for filtering. We argue that LM cross-entropy might be appropriate for LM filtering, but not as much for TM filtering. We develop a novel filtering approach based on a combined TM and LM cross-entropy scores. We experiment with two large-scale translation tasks, the Arabic-to-English and English-to-French IWSLT 2011 TED Talks MT tasks. For LM filtering, we achieve strong perplexity improvements which carry over to the translation quality with improvements up to +0.4% BLEU. For TM filtering, the combined method achieves small but consistent improvements over the standalone methods. As a side effect of adaptation via filtering, the fully fledged SMT system vocabulary size and phrase table size are reduced by a factor of at least 2 while up to +0.6% BLEU improvement is observed. © IWSLT 2011. All rights reserved.

关键词： computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

Beam search for solving substitution ciphers

Beam search for solving substitution ciphers

引用

51st Annual Meeting of the Association for Computational Linguistics, ACL 2013

作者： Nuhn, Malte Schamper, Julian Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

ISBN: (纸本)9781937284503

In this paper we address the problem of solving substitution ciphers using a beam search approach. We present a conceptually consistent and easy to implement method that improves the current state of the art for decipherment of substitution ciphers and is able to use high order n-gram language models. We show experiments with 1:1 substitution ciphers in which the guaranteed optimal solution for 3-gram language models has 38.6% decipherment error, while our approach achieves 4.13% decipherment error in a fraction of time by using a 6-gram language model. We also apply our approach to the famous Zodiac-408 cipher and obtain slightly better (and near to optimal) results than previously published. Unlike the previous state-of-the-art approach that uses additional word lists to evaluate possible decipherments, our approach only uses a letterbased 6-gram language model. Furthermore we use our algorithm to solve large vocabulary substitution ciphers and improve the best published decipherment error rate based on the Gigaword corpus of 7.8% to 6.0% error rate. © 2013 Association for Computational Linguistics.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：