The Experts below are selected from a list of 47973 Experts worldwide ranked by ideXlab platform
Min Zhang - One of the best experts on this subject based on the ideXlab platform.
-
AAAI - Neural Machine Translation advised by statistical Machine Translation
2017Co-Authors: Xing Wang, Zhaopeng Tu, Deyi Xiong, Zhengdong Lu, Hang Li, Min ZhangAbstract:Neural Machine Translation (NMT) is a new approach to Machine Translation that has made great progress in recent years. However, recent studies show that NMT generally produces fluent but inadequate Translations (Tu et al. 2016b; 2016a; He et al. 2016; Tu et al. 2017). This is in contrast to conventional Statistical Machine Translation (SMT), which usually yields adequate but non-fluent Translations. It is natural, therefore, to leverage the advantages of both models for better Translations, and in this work we propose to incorporate SMT model into NMT framework. More specifically, at each decoding step, SMT offers additional recommendations of generated words based on the decoding information from NMT (e.g., the generated partial Translation and attention history). Then we employ an auxiliary classifier to score the SMT recommendations and a gating function to combine the SMT recommendations with NMT generations, both of which are jointly trained within the NMT architecture in an end-to-end manner. Experimental results on Chinese-English Translation show that the proposed approach achieves significant and consistent improvements over state-of-the-art NMT and SMT systems on multiple NIST test sets.
-
Neural Machine Translation Advised by Statistical Machine Translation
arXiv: Computation and Language, 2016Co-Authors: Xing Wang, Zhaopeng Tu, Deyi Xiong, Zhengdong Lu, Hang Li, Min ZhangAbstract:Neural Machine Translation (NMT) is a new approach to Machine Translation that has made great progress in recent years. However, recent studies show that NMT generally produces fluent but inadequate Translations (Tu et al. 2016b; Tu et al. 2016a; He et al. 2016; Tu et al. 2017). This is in contrast to conventional Statistical Machine Translation (SMT), which usually yields adequate but non-fluent Translations. It is natural, therefore, to leverage the advantages of both models for better Translations, and in this work we propose to incorporate SMT model into NMT framework. More specifically, at each decoding step, SMT offers additional recommendations of generated words based on the decoding information from NMT (e.g., the generated partial Translation and attention history). Then we employ an auxiliary classifier to score the SMT recommendations and a gating function to combine the SMT recommendations with NMT generations, both of which are jointly trained within the NMT architecture in an end-to-end manner. Experimental results on Chinese-English Translation show that the proposed approach achieves significant and consistent improvements over state-of-the-art NMT and SMT systems on multiple NIST test sets.
-
Variational Neural Machine Translation
arXiv: Computation and Language, 2016Co-Authors: Biao Zhang, Jinsong Su, Deyi Xiong, Hong Duan, Min ZhangAbstract:Models of neural Machine Translation are often from a discriminative family of encoderdecoders that learn a conditional distribution of a target sentence given a source sentence. In this paper, we propose a variational model to learn this conditional distribution for neural Machine Translation: a variational encoderdecoder model that can be trained end-to-end. Different from the vanilla encoder-decoder model that generates target Translations from hidden representations of source sentences alone, the variational model introduces a continuous latent variable to explicitly model underlying semantics of source sentences and to guide the generation of target Translations. In order to perform efficient posterior inference and large-scale training, we build a neural posterior approximator conditioned on both the source and the target sides, and equip it with a reparameterization technique to estimate the variational lower bound. Experiments on both Chinese-English and English- German Translation tasks show that the proposed variational neural Machine Translation achieves significant improvements over the vanilla neural Machine Translation baselines.
-
Neural Machine Translation Advised by Statistical Machine Translation
Thirty-First AAAI Conference on Artificial Intelligence, 2016Co-Authors: Xing Wang, Zhaopeng Tu, Deyi Xiong, Zhengdong Lu, Hang Li, Min ZhangAbstract:Neural Machine Translation (NMT) is a new approach to Machine Translation that has made great progress in recent years. However, recent studies show that NMT generally produces fluent but inadequate Translations (Tu et al. 2016; He et al. 2016). This is in contrast to conventional Statistical Machine Translation (SMT), which usually yields adequate but non-fluent Translations. It is natural, therefore, to leverage the advantages of both models for better Translations, and in this work we propose to incorporate SMT model into NMT framework. More specifically, at each decoding step, SMT offers additional recommendations of generated words based on the decoding information from NMT (e.g., the generated partial Translation and attention history). Then we employ an auxiliary classifier to score the SMT recommendations and a gating function to combine the SMT recommendations with NMT generations, both of which are jointly trained within the NMT architecture in an end-to-end manner. Experimental results on Chinese-English Translation show that the proposed approach achieves significant and consistent improvements over state-of the-art NMT and SMT systems on multiple NIST test sets.
Masato Tokuhisa - One of the best experts on this subject based on the ideXlab platform.
-
NTCIR - Statistical Machine Translation with Rule based Machine Translation.
2020Co-Authors: Jin'ichi Murakami, Masato TokuhisaAbstract:We have evaluated the two-stage Machine Translation (MT) system. The first stage is a state-of-the-art trial rule-based Machine Translation system. The second stage is a normal statistical Machine Translation system. For Japanese-English Machine Translation, first, we used a Japanese-English rule-based MT, and we obtained "ENGLISH" sentences from Japanese sentences. Second, we used a standard statistical Machine Translation. This means that we translated "ENGLISH" to English Machine Translation. This method has an advantages that it produces grammatically correct sentences. From the results of experiments in the JE task, we obtained a BLEU score of 0.1996 using our proposed method. In contrast, we obtained a BLEU score of 0.1436 using a standard method. And for the EJ task, we obtained a BLEU score of 0.2775 using our proposed method. In contrast, we obtained a BLEU score of 0.0831 using a standard method. This means that our proposed method was effective for the JE and EJ task. However, there is a problem. The BLEU score was not so effective to measure the Translation quality.
-
NTCIR - Statistical Machine Translation Adding Rule-based Machine Translation.
2020Co-Authors: Jin'ichi Murakami, Masato Tokuhisa, Satoru IkeharaAbstract:We have developed a two-stage Machine Translation (MT) system. The first stage is a rule-based Machine Translation system. The second stage is a normal statistical Machine Translation system. For Japanese-English Machine Translation, first, we used a JapaneseEnglish rule-based MT, and we obtained "ENGLISH" sentences from Japanese sentences. Second, we used a standard statistical Machine Translation. This means that we translated "ENGLISH" to English Machine Translation. We believe this method has two advantages. One is that there are fewer unknown words. The other is that it produces structured or grammatically correct sentences. From the results of experiments, we obtained a BLEU score of 0.2565 in the Intrinsic-JE task using our proposed method. In contrast, we obtained a BLEU score of 0.2165 in the Intrinsic-JE task using a standard method (moses). And we obtained a BLEU score of 0.2602 in the Intrinsic-EJ task using our proposed method. In contrast, we obtained a BLEU score of 0.2501 in the Intrinsic-EJ task using a standard method (moses). This means that our proposed method was effective for the IntrinsicJE and Intrinsic-EJ task. For the future study, we will try to improve the performance by optimizing parameters.
-
IWSLT - Statistical pattern-based Machine Translation with statistical French-English Machine Translation.
2020Co-Authors: Jin'ichi Murakami, Takuya Nishimura, Masato TokuhisaAbstract:We developed a two-stage Machine Translation (MT) system. The first stage consists of an automatically created pattern-based Machine Translation system, and the second stage consists of a standard statistical Machine Translation (SMT) system. For French-English Machine Translation, we first used a French-English pattern-based MT, and we obtained ”English” sentences from French sentences. Second, we used a standard SMT. This means that we translated ”English” to English Machine Translation. We obtained a Bilingual Evaluation Understudy (BLEU) score of 0.5201 in the Basic Travel Expression Corpus French English (BTEC-FE) task using our proposed system. In contrast, we obtained a BLEU score of 0.5077 in the BTEC-FE task using a standard SMT system (Moses). This means that our proposed system is effective in the BTEC-FE task. However, our system placed 7th out of 9 systems.
-
IWSLT - Statistical Machine Translation adding Pattern-based Machine Translation in Chinese-English Translation
2020Co-Authors: Masato Tokuhisa, Satoru IkeharaAbstract:We have developed a two-stage Machine Translation (MT) system. The first stage is a rule-based Machine Translation system. The second stage is a normal statistical Machine Translation system. For Chinese-English Machine Translation, first, we used a Chinese-English rule-based MT, and we obtained ”ENGLISH” sentences from Chinese sentences. Second, we used a standard statistical Machine Translation. This means that we translated ”ENGLISH” to English Machine Translation. W e believe this method has two advantages. One is that there are fewer unknown words. The other is that it produces structured or grammatically correct sentences. From the results of experiments, we obtained a BLEU score of 0.3151 in the BTEC-CE task using our proposed method. In contrast, we obtained a BLEU score of 0.3311 in the BTEC-CE task using a standard method (moses). This means that our proposed method was not as effective for the BTEC-CE task. Therefore, we will try to improve the performance by optimizing parameters.
Deyi Xiong - One of the best experts on this subject based on the ideXlab platform.
-
AAAI - Neural Machine Translation advised by statistical Machine Translation
2017Co-Authors: Xing Wang, Zhaopeng Tu, Deyi Xiong, Zhengdong Lu, Hang Li, Min ZhangAbstract:Neural Machine Translation (NMT) is a new approach to Machine Translation that has made great progress in recent years. However, recent studies show that NMT generally produces fluent but inadequate Translations (Tu et al. 2016b; 2016a; He et al. 2016; Tu et al. 2017). This is in contrast to conventional Statistical Machine Translation (SMT), which usually yields adequate but non-fluent Translations. It is natural, therefore, to leverage the advantages of both models for better Translations, and in this work we propose to incorporate SMT model into NMT framework. More specifically, at each decoding step, SMT offers additional recommendations of generated words based on the decoding information from NMT (e.g., the generated partial Translation and attention history). Then we employ an auxiliary classifier to score the SMT recommendations and a gating function to combine the SMT recommendations with NMT generations, both of which are jointly trained within the NMT architecture in an end-to-end manner. Experimental results on Chinese-English Translation show that the proposed approach achieves significant and consistent improvements over state-of-the-art NMT and SMT systems on multiple NIST test sets.
-
Neural Machine Translation Advised by Statistical Machine Translation
arXiv: Computation and Language, 2016Co-Authors: Xing Wang, Zhaopeng Tu, Deyi Xiong, Zhengdong Lu, Hang Li, Min ZhangAbstract:Neural Machine Translation (NMT) is a new approach to Machine Translation that has made great progress in recent years. However, recent studies show that NMT generally produces fluent but inadequate Translations (Tu et al. 2016b; Tu et al. 2016a; He et al. 2016; Tu et al. 2017). This is in contrast to conventional Statistical Machine Translation (SMT), which usually yields adequate but non-fluent Translations. It is natural, therefore, to leverage the advantages of both models for better Translations, and in this work we propose to incorporate SMT model into NMT framework. More specifically, at each decoding step, SMT offers additional recommendations of generated words based on the decoding information from NMT (e.g., the generated partial Translation and attention history). Then we employ an auxiliary classifier to score the SMT recommendations and a gating function to combine the SMT recommendations with NMT generations, both of which are jointly trained within the NMT architecture in an end-to-end manner. Experimental results on Chinese-English Translation show that the proposed approach achieves significant and consistent improvements over state-of-the-art NMT and SMT systems on multiple NIST test sets.
-
Variational Neural Machine Translation
arXiv: Computation and Language, 2016Co-Authors: Biao Zhang, Jinsong Su, Deyi Xiong, Hong Duan, Min ZhangAbstract:Models of neural Machine Translation are often from a discriminative family of encoderdecoders that learn a conditional distribution of a target sentence given a source sentence. In this paper, we propose a variational model to learn this conditional distribution for neural Machine Translation: a variational encoderdecoder model that can be trained end-to-end. Different from the vanilla encoder-decoder model that generates target Translations from hidden representations of source sentences alone, the variational model introduces a continuous latent variable to explicitly model underlying semantics of source sentences and to guide the generation of target Translations. In order to perform efficient posterior inference and large-scale training, we build a neural posterior approximator conditioned on both the source and the target sides, and equip it with a reparameterization technique to estimate the variational lower bound. Experiments on both Chinese-English and English- German Translation tasks show that the proposed variational neural Machine Translation achieves significant improvements over the vanilla neural Machine Translation baselines.
-
Recurrent Neural Machine Translation
arxiv, 2016Co-Authors: Biao Zhang, Deyi Xiong, Jinsong SuAbstract:Models of neural Machine Translation are often from a discriminative family of encoder-decoders that learn a conditional distribution of a target sentence given a source sentence. In this paper, we propose a variational model to learn this conditional distribution for neural Machine Translation: a variational encoder-decoder model that can be trained end-to-end. Different from the vanilla encoder-decoder model that generates target Translations from hidden representations of source sentences alone, the variational model introduces a continuous latent variable to explicitly model underlying semantics of source sentences and to guide the generation of target Translations. In order to perform an efficient posterior inference, we build a neural posterior approximator that is conditioned only on the source side. Additionally, we employ a reparameterization technique to estimate the variational lower bound so as to enable standard stochastic gradient optimization and large-scale training for the variational model. Experiments on NIST Chinese-English Translation tasks show that the proposed variational neural Machine Translation achieves significant improvements over both state-of-the-art statistical and neural Machine Translation baselines.
-
Varitional Neural Machine Translation
Emnlp-2016, 2016Co-Authors: Biao Zhang, Deyi Xiong, Jinsong SuAbstract:Models of neural Machine Translation are often from a discriminative family of encoder-decoders that learn a conditional distribution of a target sentence given a source sentence. In this paper, we propose a variational model to learn this conditional distribution for neural Machine Translation: a variational encoder-decoder model that can be trained end-to-end. Different from the vanilla encoder-decoder model that generates target Translations from hidden representations of source sentences alone, the variational model introduces a continuous latent variable to explicitly model underlying semantics of source sentences and to guide the generation of target Translations. In order to perform an efficient posterior inference, we build a neural posterior approximator that is conditioned only on the source side. Additionally, we employ a reparameterization technique to estimate the variational lower bound so as to enable standard stochastic gradient optimization and large-scale training for the variational model. Experiments on NIST Chinese-English Translation tasks show that the proposed variational neural Machine Translation achieves significant improvements over both state-of-the-art statistical and neural Machine Translation baselines.
Xing Wang - One of the best experts on this subject based on the ideXlab platform.
-
AAAI - Neural Machine Translation advised by statistical Machine Translation
2017Co-Authors: Xing Wang, Zhaopeng Tu, Deyi Xiong, Zhengdong Lu, Hang Li, Min ZhangAbstract:Neural Machine Translation (NMT) is a new approach to Machine Translation that has made great progress in recent years. However, recent studies show that NMT generally produces fluent but inadequate Translations (Tu et al. 2016b; 2016a; He et al. 2016; Tu et al. 2017). This is in contrast to conventional Statistical Machine Translation (SMT), which usually yields adequate but non-fluent Translations. It is natural, therefore, to leverage the advantages of both models for better Translations, and in this work we propose to incorporate SMT model into NMT framework. More specifically, at each decoding step, SMT offers additional recommendations of generated words based on the decoding information from NMT (e.g., the generated partial Translation and attention history). Then we employ an auxiliary classifier to score the SMT recommendations and a gating function to combine the SMT recommendations with NMT generations, both of which are jointly trained within the NMT architecture in an end-to-end manner. Experimental results on Chinese-English Translation show that the proposed approach achieves significant and consistent improvements over state-of-the-art NMT and SMT systems on multiple NIST test sets.
-
Neural Machine Translation Advised by Statistical Machine Translation
arXiv: Computation and Language, 2016Co-Authors: Xing Wang, Zhaopeng Tu, Deyi Xiong, Zhengdong Lu, Hang Li, Min ZhangAbstract:Neural Machine Translation (NMT) is a new approach to Machine Translation that has made great progress in recent years. However, recent studies show that NMT generally produces fluent but inadequate Translations (Tu et al. 2016b; Tu et al. 2016a; He et al. 2016; Tu et al. 2017). This is in contrast to conventional Statistical Machine Translation (SMT), which usually yields adequate but non-fluent Translations. It is natural, therefore, to leverage the advantages of both models for better Translations, and in this work we propose to incorporate SMT model into NMT framework. More specifically, at each decoding step, SMT offers additional recommendations of generated words based on the decoding information from NMT (e.g., the generated partial Translation and attention history). Then we employ an auxiliary classifier to score the SMT recommendations and a gating function to combine the SMT recommendations with NMT generations, both of which are jointly trained within the NMT architecture in an end-to-end manner. Experimental results on Chinese-English Translation show that the proposed approach achieves significant and consistent improvements over state-of-the-art NMT and SMT systems on multiple NIST test sets.
-
Neural Machine Translation Advised by Statistical Machine Translation
Thirty-First AAAI Conference on Artificial Intelligence, 2016Co-Authors: Xing Wang, Zhaopeng Tu, Deyi Xiong, Zhengdong Lu, Hang Li, Min ZhangAbstract:Neural Machine Translation (NMT) is a new approach to Machine Translation that has made great progress in recent years. However, recent studies show that NMT generally produces fluent but inadequate Translations (Tu et al. 2016; He et al. 2016). This is in contrast to conventional Statistical Machine Translation (SMT), which usually yields adequate but non-fluent Translations. It is natural, therefore, to leverage the advantages of both models for better Translations, and in this work we propose to incorporate SMT model into NMT framework. More specifically, at each decoding step, SMT offers additional recommendations of generated words based on the decoding information from NMT (e.g., the generated partial Translation and attention history). Then we employ an auxiliary classifier to score the SMT recommendations and a gating function to combine the SMT recommendations with NMT generations, both of which are jointly trained within the NMT architecture in an end-to-end manner. Experimental results on Chinese-English Translation show that the proposed approach achieves significant and consistent improvements over state-of the-art NMT and SMT systems on multiple NIST test sets.
George Foster - One of the best experts on this subject based on the ideXlab platform.
-
A Statistical Machine Translation Primer
2020Co-Authors: Cyril Goutte, Marc Dymetman, N. Cancedda, George FosterAbstract:This first chapter is a short introduction to the main aspects of statistical Machine Translation (SMT). In particular, we cover the issues of automatic evaluation of Machine Translation output, language modeling, word-based and phrase-based Translation models, and the use of syntax in Machine Translation. We will also do a quick roundup of some more recent directions that we believe may gain importance in the future. We situate statistical Machine Translation in the general context of Machine learning research, and put the emphasis on similarities and differences with standard Machine learning problems and practice.
-
Learning Machine Translation
Neural Information Processing Series, 2009Co-Authors: Cyril Goutte, Marc Dymetman, N. Cancedda, George FosterAbstract:The Internet gives us access to a wealth of information in languages we don't understand. The investigation of automated or semi-automated approaches to Translation has become a thriving research field with enormous commercial potential. This volume investigates how Machine learning techniques can improve statistical Machine Translation, currently at the forefront of research in the field. The book looks first at enabling technologiestechnologies that solve problems that are not Machine Translation proper but are linked closely to the development of a Machine Translation system. These include the acquisition of bilingual sentence-aligned data from comparable corpora, automatic construction of multilingual name dictionaries, and word alignment. The book then presents new or improved statistical Machine Translation techniques, including a discriminative training framework for leveraging syntactic information, the use of semi-supervised and kernel-based learning methods, and the combination of multiple Machine Translation outputs in order to improve overall Translation quality.
