Filters








42,689 Hits in 5.8 sec

Guest Editors Introduction: Machine Learning in Speech and Language Technologies

Pascale Fung, Dan Roth
2005 Machine Learning  
Indeed, many of the machine learning techniques used in language processing, from statistical part-of-speech tagging to the noisy channel model for machine translation have roots in work conducted in the  ...  However, advances in learning theory and algorithmic machine learning approaches in recent years have led to significant changes in the direction and emphasis of the statistical and learning centered research  ...  Special thanks go the Machine Learning Journal editorial staff. The work of Pascale Fung was partly supported by CERG #HKUST6206/03E of the Research Grants Council of the Hong Kong government.  ... 
doi:10.1007/s10994-005-1399-6 fatcat:756wi62i6jemji4w6fwcskti2q

A SYSTEMATIC READING IN STATISTICAL TRANSLATION: FROM THE STATISTICAL MACHINE TRANSLATION TO THE NEURAL TRANSLATION MODELS

Zakaria El Maazouzi, Badr Eddine EL Mohajir, Mohammed Al Achhab
2017 Journal of Information and Communication Technology  
Automatic translation as a key application in the natural language processing domain has developed many approaches, namely statistical machine translation and recently neural machine translation that improved  ...  Achieving high accuracy in automatic translation tasks has been one of the challenging goals for researchers in the area of machine translation since decades.  ...  ACKNOWLEDGMENT We would like to acknowledge the National Center for Scientific and Technical Research (CNRST) for supporting this study under the framework of Merit Scholarship Ref: L 02/13.  ... 
doi:10.32890/jict2017.16.2.8239 fatcat:y6rqlyztnnfztofugcqhhu6qci

Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization

Jiacheng Zhang, Yang Liu, Huanbo Luan, Jingfang Xu, Maosong Sun
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
We represent prior knowledge sources as features in a log-linear model, which guides the learning process of the neural translation model.  ...  In this work, we propose to use posterior regularization to provide a general framework for integrating prior knowledge into neural machine translation.  ...  Acknowledgments We thank Shiqi Shen for useful discussions and anonymous reviewers for insightful comments.  ... 
doi:10.18653/v1/p17-1139 dblp:conf/acl/ZhangLLXS17 fatcat:o5qhg3v4hvhgjcr6tfqzor7gdy

Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization [article]

Jiacheng Zhang, Yang Liu, Huanbo Luan, Jingfang Xu, Maosong Sun
2018 arXiv   pre-print
We represent prior knowledge sources as features in a log-linear model, which guides the learning process of the neural translation model.  ...  In this work, we propose to use posterior regularization to provide a general framework for integrating prior knowledge into neural machine translation.  ...  Acknowledgments We thank Shiqi Shen for useful discussions and anonymous reviewers for insightful comments.  ... 
arXiv:1811.01100v1 fatcat:za4zbk7mwva4fem7frhl7roijq

Max Margin Learning for Statistical Machine Translation

Katsuhiko Hayashi, Taro Watanabe, Hajime Tsukada, Hideki Isozaki, Seiichi Yamamoto
2010 Transactions of the Japanese society for artificial intelligence  
In this paper, we presented a new training algorithm for statisitcal machine translation, inspired by MERT and Structural Support Vector Machines.  ...  Minimum error rate training (MERT) has been a widely used learning method for statistical machine translation to estimate the feature function weights of a linear model.  ...  the Association for Computational Linguistics, pp. 177-180 (2007) [Kudo 00] Kudo, T. and Matsumoto, Y.: Japanese Dependency Structure Analysis Based on Support Vector Machines, in Proc.  ... 
doi:10.1527/tjsai.25.593 fatcat:vb2w3vvdr5ba5djhhm2gnevyqm

Distinctive feature detection using support vector machines

P. Niyogi, C. Burges, P. Ramesh
1999 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)  
We discuss the application of the support vector machines (SVM) that arise when the structural risk minimization principle is applied to such feature detection problems.  ...  In this paper we use both linear and nonlinear SVMs for stop detection and present experimental results to show that they perform better than a cepstral features based hidden Markov model (HMM) system,  ...  Figure 3 : 3 Performance of linear support vector machines. Figure 4 : 4 Performance of linear and non-linear support vector machines against derivative operators and HMMs.  ... 
doi:10.1109/icassp.1999.758153 dblp:conf/icassp/NiyogiBR99 fatcat:c54qmhejz5d6dm43o7jqbw7ddy

Scalable Reordering Models for SMT based on Multiclass SVM

Abdullah Alrajeh, Mahesan Niranjan
2015 Prague Bulletin of Mathematical Linguistics  
Posing phrase movements as a classification problem, we exploit recent developments in solving large-scale multiclass support vector machines.  ...  In state-of-the-art phrase-based statistical machine translation systems, modelling phrase reorderings is an important need to enhance naturalness of the translated outputs, particularly when the grammatical  ...  Acknowledgements The first author was funded by a scholarship from King Abdulaziz City for Science and Technology (KACST). Bibliography  ... 
doi:10.1515/pralin-2015-0004 fatcat:juq43rhruzfvlkkylcal5f3txq

Transduction Recursive Auto-Associative Memory: Learning Bilingual Compositional Distributed Vector Representations of Inversion Transduction Grammars

Karteek Addanki, Dekai Wu
2014 Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation  
TRAAMs have properties that appear attractive for bilingual grammar induction and statistical machine translation applications.  ...  We introduce TRAAM, or Transduction RAAM, a fully bilingual generalization of Pollack's (1990) monolingual Recursive Auto-Associative Memory neural network model, in which each distributed vector represents  ...  Acknowledgments This material is based upon work supported in part by the Defense Advanced Research Projects Agency (DARPA) under BOLT contract nos.  ... 
doi:10.3115/v1/w14-4013 dblp:conf/ssst/AddankiW14 fatcat:3uy67qmcnneofmoroxbhxv77uq

A Statistical Machine Translation Primer [chapter]

Nicola Cancedda, Marc Dymetman, George Foster, Cyril Goutte
2008 Learning Machine Translation  
Chapter 9 presents a novel approach to MT that eschews the traditional log-linear combination of feature function in favour of a kernel-based approach (to our knowledge the first of its kind in the context  ...  We wish to thank the MIT Press who gave us the opportunity to publish this volume, and in particular Susan Buckley and Robert Prior for their support in preparing the manuscript.  ...  Maximum Entropy models Maximum entropy models (aka log-linear models), have been an important tool of statistical NLP since the early 90's, in particular in the context of Statistical Machine Translation  ... 
doi:10.7551/mitpress/9780262072977.003.0001 fatcat:lxpjkowiufaobddnf6xbuoc23m

On the Properties of Neural Machine Translation: Encoder–Decoder Approaches

Kyunghyun Cho, Bart van Merrienboer, Dzmitry Bahdanau, Yoshua Bengio
2014 Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation  
Neural machine translation is a relatively new approach to statistical machine translation based purely on neural networks.  ...  In this paper, we focus on analyzing the properties of the neural machine translation using two models; RNN Encoder-Decoder and a newly proposed gated recursive convolutional neural network.  ...  Acknowledgments The authors would like to acknowledge the support of the following agencies for research funding and computing support: NSERC, Calcul Québec, Compute Canada, the Canada Research Chairs  ... 
doi:10.3115/v1/w14-4012 dblp:conf/ssst/ChoMBB14 fatcat:zogr4hmywfetnfv4fk3pwho6di

Volatility Forecasting: The Support Vector Regression Can Beat the Random Walk

BEZERRA PEDRO CORREIA SANTOS, ALBUQUERQUE PEDRO HENRIQUE MELO
2019 ECONOMIC COMPUTATION AND ECONOMIC CYBERNETICS STUDIES AND RESEARCH  
In this paper, we implement a standard Support Vector Regression model with Gaussian and Morlet wavelet kernels on daily returns of two stock market indexes -USA(SP&500) and Brazil (IBOVESPA) -over the  ...  Machine learning techniques that have been employed to forecast financial volatility.  ...  The next section describes the Support Vector Machine (SVM) for regression. Section 3 describes the empirical modelling.  ... 
doi:10.24818/18423264/53.4.19.07 fatcat:tiaq7hpbeja53pgkfcw57drade

Arabic English Cross-Lingual Plagiarism Detection Based on Keyphrases Extraction, Monolingual and Machine Learning Approach

Mokhtar Al-Suhaiqi, Muneer A. S. Hazaa, Mohammed Albared
2019 Asian Journal of Research in Computer Science  
In addition, three machine learning approaches namely i) naïve Bayes, ii) Support Vector Machine, and iii) linear logistic regression classifiers are used for Arabic-English Cross-language plagiarism detection  ...  In addition, Several experiments to investigate the performance of machine learning techniques to find the best method for Arabic-English Cross-language plagiarism detection.  ...  (3.14) Support vector machines SVM is a featured machine learning technique that is developed for the binary classification task.  ... 
doi:10.9734/ajrcos/2018/v2i330075 fatcat:47grqk43mnhmxnqrpq7pnrmglu

On Using Monolingual Corpora in Neural Machine Translation [article]

Caglar Gulcehre, Orhan Firat, Kelvin Xu, Kyunghyun Cho, Loic Barrault, Huei-Chi Lin, Fethi Bougares, Holger Schwenk, Yoshua Bengio
2015 arXiv   pre-print
In this work, we investigate how to leverage abundant monolingual corpora for neural machine translation.  ...  Recent work on end-to-end neural network-based architectures for machine translation has shown promising results for En-Fr and En-De translation.  ...  Introduction Neural machine translation (NMT) is a novel approach to machine translation that has shown promising results (Kalchbrenner and Blunsom, 2013; Bahdanau et al., 2014) .  ... 
arXiv:1503.03535v2 fatcat:iv7eznysrnbr5klaf4k5thaeji

Large-scale Reordering Model for Statistical Machine Translation using Dual Multinomial Logistic Regression

Abdullah Alrajeh, Mahesan Niranjan
2014 Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)  
Phrase reordering is a challenge for statistical machine translation systems.  ...  In this paper, we explore recent advancements in solving large-scale classification problems.  ...  Advancements in solving large-scale classification problems have been shown to be effective such as dual coordinate descent method for linear support vector machines (Hsieh et al., 2008) .  ... 
doi:10.3115/v1/d14-1183 dblp:conf/emnlp/AlrajehN14 fatcat:kxn32gdgcbbz5lq4b2zu55uk5u

Exploiting lexical information for function tag labeling

Caixia Yuan, Xiaojie Wang, Fuji Ren
2008 2008 International Conference on Natural Language Processing and Knowledge Engineering  
model, another is maximum margin based support vector machine model.  ...  In order to demonstrate the effectiveness and versatility of our method, we investigate function tag assignment for unparsed Chinese text by applying two statistical models, one is log-linear maximum entropy  ...  such as information extraction, dialog system and machine translation system.  ... 
doi:10.1109/nlpke.2008.4906787 dblp:conf/nlpke/YuanWR08 fatcat:enzy737mwrcgziclohko7bxnwm
« Previous Showing results 1 — 15 out of 42,689 results