检索结果-内蒙古大学图书馆

Towards reinforcement learning for pivot-based neural machine translation with non-autoregressive transformer

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Tokarchuk, Evgeniia Rosendahl, Jan Wang, Weiyue Petrushkov, Pavel Lancewicki, Tomer Khadivi, Shahram Ney, Hermann eBay Inc Human Language Technology and Pattern Recognition Group RWTH Aachen University Germany

Pivot-based neural machine translation (NMT) is commonly used in low-resource setups, especially for translation between non-English language pairs. It benefits from using high-resource source→pivot and pivot→target language pairs and an individual system is trained for both sub-tasks. However, these models have no connection during training, and the source→pivot model is not optimized to produce the best translation for the source→target task. In this work, we propose to train a pivot-based NMT system with the reinforcement learning (RL) approach, which has been investigated for various text generation tasks, including machine translation (MT). We utilize a non-autoregressive transformer and present an end-to-end pivot-based integrated model, enabling training on source→target data. Copyright © 2021, The Authors. All rights reserved.

关键词： Neural machine translation

Offline Features for Classifying Handwritten Math Symbols with Recurrent Neural Networks

学校读者我要写书评

暂无评论

Offline Features for Classifying Handwritten Math Symbols wi...

International Conference on pattern recognition

作者： Francisco Álvaro Joan-Andreu Sánchez José-Miguel Benedí Pattern Recognition and Human Language Technologies Universitat Politècnica de València Spain

In mathematical expression recognition, symbol classification is a crucial step. Numerous approaches for recognizing handwritten math symbols have been published, but most of them are either an online approach or a hybrid approach. There is an absence of a study focused on offline features for handwritten math symbol recognition. Furthermore, many papers provide results difficult to compare. In this paper we assess the performance of several well-known offline features for this task. We also test a novel set of features based on polar histograms and the vertical repositioning method for feature extraction. Finally, we report and analyze the results of several experiments using recurrent neural networks on a large public database of online handwritten math expressions. The combination of online and offline features significantly improved the recognition rate.

关键词： Feature extraction Text recognition Vectors Handwriting recognition Hidden Markov models Databases Training

Demonstration of Joshua: An open source toolkit for parsing-based machine translation

学校读者我要写书评

暂无评论

Demonstration of Joshua: An open source toolkit for parsing-...

Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural language Processing of the AFNLP, ACL-IJCNLP 2009

作者： Li, Zhifei Callison-Burch, Chris Dyer, Chris Ganitkevitch, Juri Khudanpur, Sanjeev Schwartz, Lane Thornton, Wren N.G. Weese, Jonathan Zaidan, Omar F. Center for Language and Speech Processing Johns Hopkins University United States Computational Linguistics and Information Processing Lab. University of Maryland United States Human Language Technology and Pattern Recognition Group RWTH Aachen University Germany Natural Language Processing Lab. University of Minnesota United States

ISBN: (纸本)9781617382581

We describe Joshua (Li et al., 2009a)1, an open source toolkit for statistical machine translation. Joshua implements all of the algorithms required for translation via synchronous context free grammars (SCFGs): chart-parsing, n-gram language model integration, beam- and cubepruning, and k-best extraction. The toolkit also implements suffix-array grammar extraction and minimum error rate training. It uses parallel and distributed computing techniques for scalability. We also provide a demonstration outline for illustrating the toolkit's features to potential users, whether they be newcomers to the field or power users interested in extending the toolkit. © 2009 ACL and AFNLP.

关键词： Distributed computer systems

Data Mapping by Restricted Boltzmann Machines for Social Circles Detection

学校读者我要写书评

暂无评论

Data Mapping by Restricted Boltzmann Machines for Social Cir...

International Joint Conference on Neural Networks

作者： Jesús Alonso Roberto Paredes Paolo Rosso Pattern Recognition and Human Language Technologies Research Center Universitat Politècnica de València

ISBN: (纸本)9781479919611

Social circles detection is a special case of community detection in social network that is currently attracting a growing interest in the research community. In this paper, we propose a two-step technique, making emphasis on the mapping of the data by Restricted Boltzmann Machines (RBMs). Social circles are subsequently inferred by k-means over the preprocessed data. We define different vectorial representations from both structural egonet information and user profile features, and perform a set of tests to adjust the optimal parameters of the RBMs. We study and compare the performance on the ego-Facebook dataset of social circles from Facebook from the Stanford Large Network Dataset Collection. We compare our results with several different baselines.

关键词： Data Mapping Restricted Boltzmann Machines Social Circles Detection Boltzmann machines Circles Social Media MAPPING(MATHEMATICAL) Interest Research Facebook optimal parameter Social Networks

Py4MER: A CTC-Based Mathematical Expression recognition System 11th

学校读者我要写书评

暂无评论

Py4MER: A CTC-Based Mathematical Expression Recognition Syst...

11th Iberian Conference on pattern recognition and Image Analysis, IbPRIA 2023

作者： Anitei, Dan Sánchez, Joan Andreu Benedí, José Miguel Pattern Recognition and Human Language Technologies Research Center Universitat Politècnica València Valencia Spain Valencian Graduate School and Research Network of Artificial Intelligence Camí de Vera s/n Valencia46022 Spain

ISBN: (纸本)9783031366154

Mathematical expression recognition is a research field that aims to develop algorithms and systems capable of interpreting mathematical content. The recognition of MEs requires handling two-dimensional symbol relationships such as sub/superscripts, matrices and nested fractions, among others. The prevalent technology for addressing these challenges are based on encoder-decoder architectures with attention models. In this paper we propose the Py4MER system, based on Convolutional Recurrent Neural Network (CRNN) models, for the recognition and transcription of MEs into LaTeX mark-up sequences. This model is proposed as an alternative to encoder-decoder approaches, as CRNN models trained through Connectionist Temporal Classification (CTC) implicitly model the dependencies between symbols and do not suffer from under/over parsing of the input image, generating more consistent mark-up. The proposed model is evaluated on the Im2Latex-100k data set based on both textual and image-level metrics, showing a remarkable improvement from other CTC-based approaches. recognition results are analyzed for different ME lengths and ME structures. Furthermore, a study based on the edit distance is performed, showing a considerable improvement in precision when up to 5 edit operations are considered. Finally, we show that CTC-based CRNN models can adapt to non left-to-right ordering of ME elements, warranting more research for this approach. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Recurrent neural networks

A comparative study on vocabulary reduction for phrase table smoothing

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Kim, Yunsu Guta, Andreas Wuebker, Joern Ney, Hermann Human Language Technology and Pattern Recognition Group RWTH Aachen University Aachen Germany Lilt Inc

This work systematically analyzes the smoothing effect of vocabulary reduction for phrase translation models. We extensively compare various word-level vocabularies to show that the performance of smoothing is not significantly affected by the choice of vocabulary. This result provides empirical evidence that the standard phrase translation model is extremely sparse. Our experiments also reveal that vocabulary reduction is more effective for smoothing large-scale phrase tables. Copyright © 2019, The Authors. All rights reserved.

关键词：

Revisiting Checkpoint Averaging for Neural Machine Translation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gao, Yingbo Herold, Christian Yang, Zijian Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University Germany

Checkpoint averaging is a simple and effective method to boost the performance of converged neural machine translation models. The calculation is cheap to perform and the fact that the translation improvement almost comes for free, makes it widely adopted in neural machine translation research. Despite the popularity, the method itself simply takes the mean of the model parameters from several checkpoints, the selection of which is mostly based on empirical recipes without many justifications. In this work, we revisit the concept of checkpoint averaging and consider several extensions. Specifically, we experiment with ideas such as using different checkpoint selection strategies, calculating weighted average instead of simple mean, making use of gradient information and fine-tuning the interpolation weights on development data. Our results confirm the necessity of applying checkpoint averaging for optimal performance, but also suggest that the landscape between the converged checkpoints is rather flat and not much further improvement compared to simple averaging is to be obtained. Copyright © 2022, The Authors. All rights reserved.

关键词： Neural machine translation

Bagging by design for continuous Handwriting recognition using multi-objective particle swarm optimization

学校读者我要写书评

暂无评论

Bagging by design for continuous Handwriting Recognition usi...

International Conference on Document Analysis and recognition

作者： Mahdi Hamdani Patrick Doetsch Hermann Ney Human Language Technology and Pattern Recognition Group - RWTH Aachen University Germany Spoken Language Processing Group LIMSI CNRS Paris France

Multiple classifier systems are used to improve baseline results using different strategies. Bagging by design improves standard bagging by the minimization of intersection between the different ensembles. This work proposes the use of design bagging for continuous handwriting recognition. The design is performed using a multi-objective particle swarm optimizer. Hidden Markov Models and Long-Short Term Memory Recurrent Neural Networks are used to validate the proposed design. Experiments on English and French Handwriting recognition with different setups show significant improvements.

关键词： Lattices Optimization Optical character recognition software

Towards consistent hybrid HMM acoustic modeling

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Raissi, Tina Beck, Eugen Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Group RWTH Aachen University Germany AppTek GmbH Aachen Germany

High-performance hybrid automatic speech recognition (ASR) systems are often trained with clustered triphone outputs, and thus require a complex training pipeline to generate the clustering. The same complex pipeline is often utilized in order to generate an alignment for use in frame-wise cross-entropy training. In this work, we propose a flat-start factored hybrid model trained by modeling the full set of triphone states explicitly without relying on clustering methods. This greatly simplifies the training of new models. Furthermore, we study the effect of different alignments used for Viterbi training. Our proposed models achieve competitive performance on the Switchboard task compared to systems using clustered triphones and other flat-start models in the *** Codes 68T10 Copyright © 2021, The Authors. All rights reserved.

关键词： Pipelines