检索结果-内蒙古大学图书馆

7th Workshop on Statistical Machine Translation, WMT 2012, immediately following the Conference of the North-American Chapter of the Association for Computational Linguistics - human language Technologies, NAACL HLT 2012

作者： Huck, Matthias Peitz, Stephan Freitag, Markus Nuhn, Malte Ney, Hermann Computer Science Department Human Language Technology And Pattern Recognition Group Rwth Aachen University AachenD-52056 Germany

ISBN: (纸本)9781937284206

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. ©2012 Association for Computational Linguistics.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

The RWTH Aachen University Supervised Machine Translation Systems for WMT 2018 3

The RWTH Aachen University Supervised Machine Translation Sy...

引用

3rd Conference on Machine Translation, WMT 2018 at the Conference on Empirical Methods in Natural language Processing, EMNLP 2018

作者： Schamper, Julian Rosendahl, Jan Bahar, Parnia Kim, Yunsu Nix, Arne Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University AachenD-52056 Germany

ISBN: (纸本)9781948087810

This paper describes the statistical machine translation systems developed at RWTH Aachen University for the German→English, English→Turkish and Chinese→English translation tasks of the EMNLP 2018 Third Conference on Machine Translation (WMT 2018). We use ensembles of neural machine translation systems based on the Transformer architecture. Our main focus is on the German→English task where we scored first with respect to all automatic metrics provided by the organizers. We identify data selection, fine-tuning, batch size and model dimension as important hyperparameters. In total we improve by 6.8% BLEU over our last year’s submission and by 4.8% BLEU over the winning system of the 2017 German→English task. In English→Turkish task, we show 3.6% BLEU improvement over the last year’s winning system. We further report results on the Chinese→English task where we improve 2.2% BLEU on average over our baseline systems but stay behind the 2018 winning systems. ©2018 Association for Computational Linguistics

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

KimCHI: A sketch-based developmental skill classifier to enhance pen-driven educational interfaces for children 13

KimCHI: A sketch-based developmental skill classifier to enh...

引用

International Symposium Sketch-Based Interfaces and Modeling, SBIM 2013 - Part of the Joint Symposium on Computational Aesthetics, Sketch-Based Interfaces and Modeling, and Non-Photorealistic Animation and Rendering, Expressive 2013

作者： Kim, Hong-Hoe Taeley, Paul Valentinez, Stephanie Mctiguex, Erin Hammond, Tracy Department of Computer Science Texas AandM University United States Department of Education and Human Development Texas AandM University United States

ISBN: (纸本)9781450322058

Sketching is one of the many valuable lifelong skills that children require in their overall development, and many educational psychologists manually analyze children's sketches to assess their developmental progress. The disadvantages of manual assessment are that it is time-consuming and prone to human error and bias, so intelligent sketching interfaces have strong potential in automating this process. Unfortunately, current sketch recognition techniques concentrate solely on recognizing the meaning of sketches, rather than the sketcher's developmental skill;and do not perform well on children's sketched input, as most are trained on and developed for adult's sketches. We introduce our proposed solution called KimCHI, a specialized sketch classification technique which utilizes a sketching interface for assessing the developmental skills of children from their sketches. Our approach relies on sketch feature selection to automatically classify the developmental progress of children's sketches as either developmental or mature. We evaluated our classifiers through a user study, and our classifiers were able to differentiate the users' development skill and gender with reasonable accuracy. We subsequently created an initial sketching interface utilizing our specialized classifier called EasySketch for demonstrating educational applications to assist children in developing their sketching skills. Copyright © ACM.

关键词： EasySketch age and gender difference KimCHI: children's developmental skill classifier

来源：评论

学校读者我要写书评

暂无评论

Cross-lingual annotation projection for weakly-supervised relation extraction

Cross-lingual annotation projection for weakly-supervised re...

引用

作者： Kim, Seokhwan Jeong, Minwoo Lee, Jonghoon Lee, Gary Geunbae Human Language Technology Department Institute for Infocomm Research Singapore Microsoft Bing United States Department of Computer Science and Engineering Pohang University of Science and Technology Korea Republic of

Although researchers have conducted extensive studies on relation extraction in the last decade, statistical systems based on supervised learning are still limited, because they require large amounts of training data to achieve high performance level. In this article, we propose cross-lingual annotation projection methods that leverage parallel corpora to build a relation extraction system for a resource-poor language without significant annotation efforts. To make our method more reliable, we introduce two types of projection approaches with noise reduction strategies. We demonstrate the merit of our method using a Korean relation extraction system trained on projected examples from an English-Korean parallel corpus. Experiments show the feasibility of our approaches through comparison to other systems based on monolingual resources. © 2014 ACM.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Investigations on sequence training of neural networks 40

Investigations on sequence training of neural networks

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Wiesler, Simon Golik, Pavel Schluter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany LIMSI CNRS Spoken Language Processing Group Paris France

ISBN: (纸本)9781467369978

In this paper we present an investigation of sequence-discriminative training of deep neural networks for automatic speech recognition. We evaluate different sequence-discriminative training criteria (MMI and MPE) and optimization algorithms (including SGD and Rprop) using the RASR toolkit. Further, we compare the training of the whole network with that of the output layer only. Technical details necessary for a robust training are studied, since there is no consensus yet on the ultimate training recipe. The investigation extends our previous work on training linear bottleneck networks from scratch showing the consistently positive effect of sequence training. © 2015 IEEE.

关键词： deep neural networks optimization sequence training speech recognition

来源：评论

学校读者我要写书评

暂无评论

Improved strategies for a zero oov rate LVCSR system 40

Improved strategies for a zero oov rate LVCSR system

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Shaik, M. Ali Basha Mousa, Amr El-Desoky Hahn, Stefan Schluter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition - Computer Science Department RWTH Aachen University Aachen Germany Spoken Language Processing Group LIMSI CNRS Paris France

ISBN: (纸本)9781467369978

In this work, multiple hierarchical language modeling strategies for a zero OOV rate large vocabulary continuous speech recognition system are investigated. In our previously proposed hierarchical approach, a full-word language model and a context independent character-level LM (CLM) are directly used during search. The novelty of this work is to jointly model the character-level prior and the pronunciation probabilities, to introduce across-word context into the characterlevel LM, and to properly normalize the character-level LM using prefix-tree based normalization for the hierarchical approach. Significant reductions in-terms of word error rates (WER) on the best full-word Quaero Polish LVCSR system are reported. © 2015 IEEE.

关键词： hierarchical LVCSR OOV prefix-tree

来源：评论

学校读者我要写书评

暂无评论

RWTHLM - The RWTH Aachen University neural network language modeling toolkit 15

RWTHLM - The RWTH Aachen University neural network language ...

引用

15th Annual Conference of the International Speech Communication Association: Celebrating the Diversity of Spoken languages, INTERSPEECH 2014

作者： Sundermeyer, Martin Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany Spoken Language Processing Group LIMSI CNRS Paris France

We present a novel toolkit that implements the long short-term memory (LSTM) neural network concept for language modeling. The main goal is to provide a software which is easy to use, and which allows fast training of standard recurrent and LSTM neural network language models. The toolkit obtains state-of-the-art performance on the standard Treebank corpus. To reduce the training time, BLAS and related libraries are supported, and it is possible to evaluate multiple word sequences in parallel. In addition, arbitrary word classes can be used to speed up the computation in case of large vocabulary sizes. Finally, the software allows easy integration with SRILM, and it supports direct decoding and rescoring of HTK lattices. The toolkit is available for download under an open source license. Copyright © 2014 ISCA.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Morpheme level hierarchical pitman-Yor class-based language models for LVCSR of morphologically rich languages

Morpheme level hierarchical pitman-Yor class-based language ...

引用

14th Annual Conference of the International Speech Communication Association, INTERSPEECH 2013

作者： El-Desoky Mousa, Amr Shaik, M. Ali Basha Schlüter, Ralf Ney, Hermann Computer Science Department Human Language Technology and Pattern Recognition RWTH Aachen University Aachen Germany Spoken Language Processing Group LIMSI CNRS Paris France

Performing large vocabulary continuous speech recognition (LVCSR) for morphologically rich languages is considered a challenging task. The morphological richness of such languages leads to high out-of-vocabulary (OOV) rates and poor language model (LM) probabilities. In this case, the use of morphemes has been shown to increase the lexical coverage and lower the LM perplexity. Another approach used to improve the LM probability estimates is to incorporate additional knowledge sources in the LM estimation process using classbased LMs (CLMs). Recently, the hierarchical Pitman-Yor LMs (HPYLMs) have shown superiority over the modified Kneser- Ney (MKN) smoothed N-gram LMs in terms of both perplexity (PPL) and word error rate (WER) on word-based LVCSR tasks. In this paper, hierarchical Pitman-Yor class-based LMs (HPYCLMs) are combined with morpheme level language modeling. This enables the application of the proposed models on top of morpheme-based systems. Experiments are conducted on Arabic and German LVCSR tasks. Consistent performance improvements are obtained for all the available corpora compared to the conventional morpheme-based and class-based LMs. Copyright © 2013 ISCA.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Rich morphological tagger for english: Exploring the cross-linguistic tradeoff between morphology and syntax 15

Rich morphological tagger for english: Exploring the cross-l...

引用

15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017

作者： Kirov, Christo Sylak-Glassman, John Knowles, Rebecca Cotterell, Ryan Post, Matt Center for Language and Speech Processing United States Department of Computer Science United States Human Language Technology Center of Excellence Johns Hopkins University United States

ISBN: (纸本)9781510838604

A traditional claim in linguistics is that all human languages are equally expressive- able to convey the same wide range of meanings. Morphologically rich languages, such as Czech, rely on overt inflectional and derivational morphology to convey many semantic distinctions. languages with comparatively limited morphology, such as English, should be able to accomplish the same using a combination of syntactic and contextual cues. We capitalize on this idea by training a tagger for English that uses syntactic features obtained by automatic parsing to recover complex morphological tags projected from Czech. The high accuracy of the resulting model provides quantitative confirmation of the underlying linguistic hypothesis of equal expressivity, and bodes well for future improvements in downstream HLT tasks including machine translation. © 2017 Association for Computational Linguistics.

关键词： Morphology

来源：评论

学校读者我要写书评

暂无评论

Performing aggregation and ellipsis using discourse structures

引用

Research on language and Computation 2006年第4期4卷 353-375页

作者： Theune, Mariët Hielkema, Feikje Hendriks, Petra Human Media Interaction Department of Computer Science University of Twente Enschede Netherlands Department of Computing Science University of Aberdeen Aberdeen United Kingdom Center for Language and Cognition Groningen University of Groningen Groningen Netherlands

This article describes the generation of aggregated and elliptic sentences, using Dependency Trees connected by rhetorical relations as input. The system we have developed can generate both hypotactic and paratactic constructions with appropriate cue words, and various forms of ellipsis such as Gapping and Conjunction Reduction. We contend that Dependency Trees connected by rhetorical relations are excellent input for a generation system that has to generate ellipsis, and we propose a taxonomy of the most common Dutch cue words, grouped according to the kind of discourse relations they signal. Finally, we argue that syntactic aggregation should be performed in the Surface Realizer of a language generation system, because it requires access to language-specific syntactic information. © Springer science+Business Media 2007.

关键词： Aggregation Dependency trees Discourse structure Ellipsis language generation

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：