Filters








20,543 Hits in 4.0 sec

Content Word Aware Neural Machine Translation

Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita
2020 Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics   unpublished
Neural machine translation (NMT) encodes the source sentence in a universal way to generate the target sentence word-byword.  ...  To address this limitation, we first utilize word frequency information to distinguish between content and function words in a sentence, and then design a content word-aware NMT to improve translation  ...  "Toward Intelligent Machine Translation".  ... 
doi:10.18653/v1/2020.acl-main.34 fatcat:5f5ztquozvfdnh4diisdifs2vy

Morphology-aware Word-Segmentation in Dialectal Arabic Adaptation of Neural Machine Translation

Ahmed Tawfik, Mahitab Emam, Khaled Essam, Robert Nabil, Hany Hassan
2019 Proceedings of the Fourth Arabic Natural Language Processing Workshop  
Parallel corpora available for building machine translation (MT) models for dialectal Arabic (DA) are rather limited.  ...  This paper compares morphologyaware DA word segmentation to other word segmentation approaches like Byte Pair Encoding (BPE) and Sub-word Regularization (SR).  ...  Section 3 reviews the neural machine translation approach that we use to train and adapt translation models for dialectal Arabic.  ... 
doi:10.18653/v1/w19-4602 dblp:conf/wanlp/TawfikEENH19 fatcat:hrnonaofrjdyfnumtndaejywte

Assessing the Tolerance of Neural Machine Translation Systems Against Speech Recognition Errors [article]

Nicholas Ruiz, Mattia Antonino Di Gangi, Nicola Bertoldi, Marcello Federico
2019 arXiv   pre-print
We introduce and motivate interesting problems one faces when considering the translation of automatic speech recognition (ASR) outputs on neural machine translation (NMT) systems.  ...  While the evaluation of neural machine translation systems on textual inputs is actively researched in the literature , little has been discovered about the complexities of translating spoken language  ...  In utterance U4, NEU-RAL is missing the translation of two content words from its vocabulary.  ... 
arXiv:1904.10997v1 fatcat:dqx755bvavdmlo2wz4rftgw42y

Machine translation [article]

Mikel L. Forcada Zubizarreta
2022 Zenodo  
It also describes the main technological approaches: on the one hand, rule-based machine translation and, on the other hand, corpus-based machine translation in its two flavours: statistical and neural  ...  , to make sense of web content written in a different language.  ...  Neural machine translation The new neural MT has been commercially exploited since 2016.  ... 
doi:10.5281/zenodo.6369129 fatcat:b6kieftupzbxjdardgi7ohcuau

hyperdoc2vec: Distributed Representations of Hypertext Documents [article]

Jialong Han, Yan Song, Wayne Xin Zhao, Shuming Shi, Haisong Zhang
2018 arXiv   pre-print
., 2007) of machine translation. However, the additional words "machine translation" lead both w2v and d2v-cac to recommend many machine translation papers.  ...  our model by computing the machine translation BLEU score using the Moses system … … machine translation BLEU score … … Moses system … (c) Context as content. i.e., W ∪D.  ... 
arXiv:1805.03793v1 fatcat:gqutgjss45alvmjzuxi5exuh3i

hyperdoc2vec: Distributed Representations of Hypertext Documents

Jialong Han, Yan Song, Wayne Xin Zhao, Shuming Shi, Haisong Zhang
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
., 2007) of machine translation. However, the additional words "machine translation" lead both w2v and d2v-cac to recommend many machine translation papers.  ...  our model by computing the machine translation BLEU score using the Moses system … … machine translation BLEU score … … Moses system … (c) Context as content. i.e., W ∪D.  ... 
doi:10.18653/v1/p18-1222 dblp:conf/acl/ShiSZZH18 fatcat:aqn66zhzhzgkzmrhvwnlo5pbjm

Neural Machine Translation model for University Email Application [article]

Sandhya Aneja and Siti Nur Afikah Bte Abdul Mazid and Nagender Aneja
2020 arXiv   pre-print
A state-of-the-art Sequence-to-Sequence Neural Network for ML -> EN and EN -> ML translations is compared with Google Translate using Gated Recurrent Unit Recurrent Neural Network machine translation model  ...  In this paper, a regional vocabulary-based application-oriented Neural Machine Translation (NMT) model is proposed over the data set of emails used at the University for communication over a period of  ...  neural machine translation model.  ... 
arXiv:2007.16011v1 fatcat:ctsgb63i4nf7pc6g5fvdrxc3cy

Table of Contents [EDICS]

2020 IEEE/ACM Transactions on Audio Speech and Language Processing  
Liu 2438 Machine Translation for Spoken and Written Language Neural Machine Translation With Noisy Lexical Constraints . . . . . . . . . . . . . . . . . . . . . H. Li, G. Huang, D. Cai, and L.  ...  Liu 1864 A Novel Sentence-Level Agreement Architecture for Neural Machine Translation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/taslp.2020.3046150 fatcat:easrxuwl6zdppejsrf4bskxfw4

Neural Machine Translation with Reordering Embeddings

Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Improved neural machine translation with a syntax-aware encoder and decoder.  ...  The reordering model plays an important role in phrase-based statistical machine translation. However, there are few works that exploit the reordering information in neural machine translation.  ...  "Toward Intelligent Machine Translation".  ... 
doi:10.18653/v1/p19-1174 dblp:conf/acl/ChenWUS19 fatcat:d3dmjikazfd7dgz73acinb3j2y

Machine Translation at Booking.com: Journey and Lessons Learned [article]

Pavel Levin, Nishikant Dhanuka, Maxim Khalilov
2017 arXiv   pre-print
We describe our recently developed neural machine translation (NMT) system and benchmark it against our own statistical machine translation (SMT) system as well as two other general purpose online engines  ...  (statistical and neural).  ...  Related work Despite being relatively young, neural machine translation (NMT) has been quickly gaining popularity over statistical machine translation (SMT) both in academic circles and in the industry  ... 
arXiv:1707.07911v1 fatcat:czmbqmtozjbwhd7d5bhrxqqe4u

Memory-Augmented Neural Networks for Machine Translation [article]

Mark Collier, Joeran Beel
2019 arXiv   pre-print
We evaluate direct application of Neural Turing Machines (NTM) and Differentiable Neural Computers (DNC) to machine translation.  ...  Interestingly, our analysis shows that despite being equipped with additional flexibility and being randomly initialized memory augmented neural networks learn an algorithm for machine translation almost  ...  We evaluate direct application of Neural Turing Machines (NTM) and Differentiable Neural Computers (DNC) to machine translation.  ... 
arXiv:1909.08314v1 fatcat:t2h43nqzq5dazn77nse3olszoa

Content enhancement with augmented reality and machine learning

Justin Freeman
2020 Journal of Southern Hemisphere Earth System Science  
Advances in machine learning methods and neural network architectures have facilitated fast and accurate object and image detection, recognition and classification, as well as providing machine translation  ...  Content enhancement of real-world environments is demonstrated through the combination of machine learning methods with augmented reality displays.  ...  Wider applications of machine learning have advanced the fields of natural language processing, machine translation and understanding.  ... 
doi:10.1071/es19046 fatcat:v5zqdqb7rzcshelq6nnq72fpky

Table of Contents

2021 IEEE/ACM Transactions on Audio Speech and Language Processing  
Scharenborg Machine Translation for Spoken and Written Language Neural Machine Translation With Explicit Phrase Alignment . . ....J. Zhang, H. Luan, M. Sun, F. Zhai, J. Xu, and Y.  ...  Liu Detecting Source Contextual Barriers for Understanding Neural Machine Translation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/taslp.2021.3137066 fatcat:ocit27xwlbagtjdyc652yws4xa

Self-Attentive Residual Decoder for Neural Machine Translation

Lesly Miculicich Werlen, Nikolaos Pappas, Dhananjay Ram, Andrei Popescu-Belis
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)  
Neural sequence-to-sequence networks with attention have achieved remarkable performance for machine translation.  ...  The residual learning facilitates the flow of information from the distant past and is able to emphasize any of the previously translated words, hence it gains access to a wider context.  ...  Introduction Neural machine translation (NMT) has recently become the state-of-the-art approach to machine translation (Bojar et al., 2016) .  ... 
doi:10.18653/v1/n18-1124 dblp:conf/naacl/WerlenPRP18 fatcat:3cqj6safpzci3cqmiuia4szsjq

Research on Business English Translation Architecture Based on Artificial Intelligence Speech Recognition and Edge Computing

Yunwei Xu
2021 Wireless Communications and Mobile Computing  
Business English translation is therefore valued by translation researchers and translators.  ...  First of all, considering the relevance and complementarity between speech and text modalities, this paper uses the deep neural network feature fusion method to effectively fuse the extracted monomodal  ...  He claimed that business English includes language knowledge, communication skills, professional content, management skills, and cultural awareness, in other words, marketing and investment, foreign insurance  ... 
doi:10.1155/2021/5518868 doaj:4baa7b5b21904fd498c16ca0d2966f41 fatcat:lbynlbwfk5cvzpp2456ufj5rmy
« Previous Showing results 1 — 15 out of 20,543 results