检索结果-内蒙古大学图书馆

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

作者： Voigtlaender, Paul Doetsch, Patrick Wiesler, Simon 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

We investigate sequence-discriminative training of long shortterm memory recurrent neural networks using the maximum mutual information criterion. We show that although recurrent neural networks already make use of the whole observation sequence and are able to incorporate more contextual information than feed forward networks, their performance can be improved with sequence-discriminative training. Experiments are performed on two publicly available handwriting recognition tasks containing English and French handwriting. On the English corpus, we obtain a relative improvement in WER of over 11% with maximum mutual information (MMI) training compared to cross-entropy training. On the French corpus, we observed that it is necessary to interpolate the MMI objective function with cross-entropy. © 2015 IEEE.

关键词： handwriting recognition long shortterm memory recurrent neural networks sequence-discriminative training

来源：评论

学校读者我要写书评

暂无评论

Feature-rich sub-lexical language models using a maximum entropy approach for German LVCSR

Feature-rich sub-lexical language models using a maximum ent...

引用

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

作者： Shaik, M. Ali Basha El-Desoky Mousa, Amr 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

German is a morphologically rich language having a high degree of word inflections, derivations and compounding. This leads to high out-of-vocabulary (OOV) rates and poor language model (LM) probabilities in the large vocabulary continuous speech recognition (LVCSR) systems. One of the main challenges in the German LVCSR is the recognition of the OOV words. For this purpose, data-driven morphemes are used to provide higher lexical coverage. On the other hand, the probability estimates of a sub-lexical LM could be further improved using feature-rich LMs like maximum entropy (MaxEnt) and class-based LMs. In this work, for a sub-lexical level German LVCSR task, we investigate the use of the multiple morpheme level features as classes for building class-based LMs that are estimated using the state-of-the-art MaxEnt approach. Thus, the benefits of both the MaxEnt LMs and the traditional class-based LMs are effectively combined. Furthermore, we experiment the use of Maximum a-posteriori adaptation over the MaxEnt class-based LMs. We show consistent reductions in both the OOV recognition error rate and the word error rate (WER) on a German LVCSR task from the Quaero project, compared to the traditional class-based and the N-gram morpheme based LM. Copyright © 2013 ISCA.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Integrating Gaussian mixtures into deep neural networks: Softmax layer with hidden variables 40

Integrating Gaussian mixtures into deep neural networks: Sof...

引用

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

作者： Tuske, Zoltan Tahir, Muhammad Ali 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 the hybrid approach, neural network output directly serves as hidden Markov model (HMM) state posterior probability estimates. In contrast to this, in the tandem approach neural network output is used as input features to improve classic Gaussian mixture model (GMM) based emission probability estimates. This paper shows that GMM can be easily integrated into the deep neural network framework. By exploiting its equivalence with the log-linear mixture model (LMM), GMM can be transformed to a large softmax layer followed by a summation pooling layer. Theoretical and experimental results indicate that the jointly trained and optimally chosen GMM and bottleneck tandem features cannot perform worse than a hybrid model. Thus, the question 'hybrid vs. tandem' simplifies to optimizing the output layer of a neural network. Speech recognition experiments are carried out on a broadcast news and conversations task using up to 12 feed-forward hidden layers with sigmoid and rectified linear unit activation functions. The evaluation of the LMM layer shows recognition gains over the classic softmax output. © 2015 IEEE.

关键词： ASR bottleneck DNN GMM hybrid LMM Log-linear mixture model neural network tandem

来源：评论

学校读者我要写书评

暂无评论

TransCell:In Silico Characterization of Genomic Landscape and Cellular Responses by Deep Transfer Learning

引用

Genomics, Proteomics & Bioinformatics 2024年第2期22卷 157-170页

作者： Shan-Ju Yeh Shreya Paithankar Ruoqiao Chen Jing Xing Mengying Sun Ke Liu Jiayu Zhou Bin Chen Department of Pediatrics and Human Development Michigan State UniversityGrand RapidsMI 49503USA Department of Pharmacology and Toxicology Michigan State UniversityGrand RapidsMI 49503USA Department of Computer Science and Engineering Michigan State UniversityEast LansingMI 48824USA

Gene expression profiling of new or modified cell lines becomes routine today;however,obtaining comprehensive molecular characterization and cellular responses for a variety of cell lines,including those derived from underrepresented groups,is not trivial when resources are *** gene expression to predict other measurements has been actively explored;however,systematic investigation of its predictive power in various measurements has not been well ***,we evaluated commonly used machine learning methods and presented TransCell,a two-step deep transfer learning framework that utilized the knowledge derived from pan-cancer tumor samples to predict molecular features and *** these models,TransCell had the best performance in predicting metabolite,gene effect score(or genetic dependency),and drug sensitivity,and had comparable performance in predicting mutation,copy number variation,and protein ***,TransCell improved the performance by over 50%in drug sensitivity prediction and achieved a correlation of 0.7 in gene effect score ***,predicted drug sensitivities revealed potential repurposing candidates for new 100 pediatric cancer cell lines,and predicted gene effect scores reflected BRAF resistance in melanoma cell ***,we investigated the predictive power of gene expression in six molecular measurement types and developed a web portal(http://***/transcell/)that enables the prediction of 352,000 genomic and cellular response features solely from gene expression profiles.

关键词： Genomics Transcriptomics Cancer dependency Drug repurposing Transfer learning

来源：评论

学校读者我要写书评

暂无评论

An Information-Theoretic Empirical Analysis of Dependency-Based Feature Types for Word Prediction Models

An Information-Theoretic Empirical Analysis of Dependency-Ba...

引用

1999 Joint SIGDAT Conference on Empirical Methods in Natural language Processing and Very Large Corpora, EMNLP 1999

作者： Wu, Dekai Zhao, Jun Sui, Zhifang Human Language Technology Center Department of Computer Science University of Science and Technology HKUST Clear Water Bay Hong Kong Computational Linguistics Institute Department of Computer Science and Technology Peking University Beijing100871 China

Over the years, many proposals have been made to incorporate assorted types of feature in language models. However, discrepancies between training sets, evaluation criteria, algorithms, and hardware environments make it difficult to compare the models objectively. In this paper, we take an information theoretic approach to select feature types in a systematic manner. We describe a quantitative analysis of the information gain and the information redundancy for various combinations of feature types inspired by both dependency structure and bigram structure, using a Chinese treebank and taking word prediction as the object. The experiments yield several conclusions on the predictive value of several feature types and feature types combinations for word prediction, which are expected to provide guidelines for feature type selection in language modeling. © 1999 Proceedings of the 1999 Joint SIGDAT Conference on Empirical Methods in Natural language Processing and Very Large Corpora, EMNLP 1999. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Improving statistical machine translation using word sense disambiguation

Improving statistical machine translation using word sense d...

引用

2007 Joint Conference on Empirical Methods in Natural language Processing and Computational Natural language Learning, EMNLP-CoNLL 2007

作者： Carpuat, Marine Wu, Dekai Department of Computer Science and Engineering Human Language Technology Center HKUST University of Science and Technology Clear Water Bay Hong Kong Hong Kong

We show for the first time that incorporating the predictions of a word sense disambiguation system within a typical phrase-based statistical machine translation (SMT) model consistently improves translation quality across all three different IWSLT Chinese-English test sets, as well as producing statistically significant improvements on the larger NIST Chinese-English MT task-and moreover never hurts performance on any test set, according not only to BLEU but to all eight most commonly used automatic evaluation metrics. Recent work has challenged the assumption that word sense disambiguation (WSD) systems are useful for SMT. Yet SMT translation quality still obviously suffers from inaccurate lexical choice. In this paper, we address this problem by investigating a new strategy for integrating WSD into an SMT system, that performs fully phrasal multi-word disambiguation. Instead of directly incorporating a Senseval-style WSD system, we redefine the WSD task to match the exact same phrasal translation disambiguation task faced by phrase-based SMT systems. Our results provide the first known empirical evidence that lexical semantics are indeed useful for SMT, despite claims to the contrary. © 2007 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Improved combinatory categorial grammar induction with boundary words and bayesian inference

Improved combinatory categorial grammar induction with bound...

引用

24th International Conference on Computational Linguistics, COLING 2012

作者： Huang, Yun Zhang, Min Tan, Chew Lim Department of Computer Science National University of Singapore 13 Computing Drive Singapore Institute for Infocomm Research Human Language Department 1 Fusionopolis Way Singapore

Combinatory Categorial Grammar (CCG) is an expressive grammar formalism which is able to capture long-range dependencies. However, building large and wide-coverage treebanks for CCG is expensive and time-consuming. In this paper, we focus on the problem of unsupervised CCG induction from plain texts. Based on the baseline model in (Bisk and Hockenmaier, 2012), we propose following two improvements: (1) we utilize boundary part-of-speech (POS) tags to capture lexical information;(2) we perform nonparametric Bayesian inference based on the Pitman-Yor process to learn compact grammars. Experiments on English Penn treebank demonstrate the effectiveness of our boundary model and Bayesian learning. © 2012 The COLING.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

MT model space: Statistical versus compositional versus example-based machine translation

MT model space: Statistical versus compositional versus exam...

引用

作者： Wu, Dekai Department of Computer Science HKUST Human Language Technology Center Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong

We offer a perspective on EBMT from a statistical MT standpoint, by developing a three-dimensional MT model space based on three pairs of definitions: (1) logical versus statistical MT, (2) schema-based versus example-based MT, and (3) lexical versus compositional MT. Within this space we consider the interplay of three key ideas in the evolution of transfer, example-based, and statistical approaches to MT. We depict how all translation models face these issues in one way or another, regardless of the school of thought, and suggest where the real questions for the future may lie. © Springer science+Business Media 2007.

关键词： Translation (languages)

来源：评论

学校读者我要写书评

暂无评论

Boosting for Chinese named entity recognition 5

Boosting for Chinese named entity recognition

引用

5th SIGHAN Workshop on Chinese language Processing, co-located with COLING/ACL 2006

作者： Yu, Xiaofeng Carpuat, Marine Wu, Dekai Human Language Technology Center HKUST Department of Computer Science and Engineering University of Science and Technology Clear Water Bay Hong Kong Hong Kong

ISBN: (纸本)1932432701

We report an experiment in which a high-performance boosting based NER model originally designed for multiple European languages is instead applied to the Chinese named entity recognition task of the third SIGHAN Chinese language processing bakeoff. Using a simple character-based model along with a set of features that are easily obtained from the Chinese input strings, the system described employs boosting, a promising and theoretically well-founded machine learning method to combine a set of weak classifiers together into a final system. Even though we did no other Chinese-specific tuning, and used only one-third of the MSRA and CityU corpora to train the system, reasonable results are obtained. Our evaluation results show that 75.07 and 80.51 overall F-measures were obtained on MSRA and CityU test sets respectively. © 2006 Association for Computational Linguistics.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

BESTCUT: A graph algorithm for coreference resolution

BESTCUT: A graph algorithm for coreference resolution

引用

11th Conference on Empirical Methods in Natural language Proceessing, EMNLP 2006, Held in Conjunction with COLING/ACL 2006

作者： Nicolae, Cristina Nicolae, Gabriel Human Language Technology Research Institute Department of Computer Science University of Texas at Dallas Richardson TX 75083-0688 United States

ISBN: (纸本)1932432736

In this paper we describe a coreference resolution method that employs a classification and a clusterization phase. In a novel way, the clusterization is produced as a graph cutting algorithm, in which nodes of the graph correspond to the mentions of the text, whereas the edges of the graph constitute the confidences derived from the coreference classification. In experiments, the graph cutting algorithm for coreference resolution, called BESTCUT, achieves state-of-the-art performance. © 2006 Association for Computational Linguistics.

关键词： Graphic methods

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：