Continuous Space Translation Models for Phrase-Based Statistical Machine Translation

By Holger Schwenk. 2012

134 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Neural Machine Translation by Jointly Learning to Align and Translate (2014, methodology): “For instance, Schwenk (2012) proposed using a feedforward neural network to compute the score of a pair of source and target phrases and to use the score as an additional feature in the phrase-based statistical machine translation system.”
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation (2014, methodology): “Before presenting the empirical results, we discuss a number of recent works that have proposed to use neural networks in the context of SMT. Schwenk in (Schwenk, 2012) proposed a similar approach of scoring phrase pairs.”
A Convolutional Neural Network for Modelling Sentences (2014, methodology): “Besides comprising powerful classifiers as part of their architecture, neural sentence models can be used to condition a neural language model to generate sentences word by word (Schwenk, 2012; Mikolov and Zweig, 2012; Kalchbrenner and Blunsom, 2013a).”
Recurrent Continuous Translation Models (2013, methodology): “Phrase-based continuous translation models were ﬁrst proposed in (Schwenk et al., 2006) and re-1700 cently further developed in (Schwenk, 2012; Le et al., 2012).”
Addressing the Rare Word Problem in Neural Machine Translation (2014, background): “In recent years, MT researchers have been seeking to incorporate neural network models into the standard pipeline as an additional subcomponent [20, 21, 23, 6].”
On Using Monolingual Corpora in Neural Machine Translation (2015, methodology): “…the application of neural networks to machine translation Equal contribution † Work done while author was at Universit ´ e de Montr ´ eal was restricted to extend standard machine translation tools for rescoring translation hypotheses or reranking n-best lists (see, e.g., Schwenk, 2012, 2007a).”
Phrase-Based & Neural Unsupervised Machine Translation (2018, methodology): “In our work we also expand phrase tables, but we initialize them with an inferred bilingual unigram dictionary, following older work from the connectionist community aiming at improving PBSMT with neural models (Schwenk, 2012; Kalchbrenner and Blunsom, 2013; Cho et al., 2014).”
Fast and Robust Neural Network Joint Models for Statistical Machine Translation (2014, background): “Schwenk (2012) predicts an entire target phrase at a time, rather than a word at a time.”
Deep Learning: Methods and Applications (2014, methodology): “A related approach to machine translation was developed by Schwenk [320].”
Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement (2018, background): “Non-Autoregressive Neural Machine Translation Schwenk (2012) proposed a continuous-space translation model to estimate the conditional distribution over a target phrase given a source phrase, while dropping the conditional dependencies among target tokens.”
Learning Continuous Phrase Representations for Translation Modeling (2014, methodology): “…the CPTM is learning the continuous representation of a phrase that is effective for SMT. Motivated by recent studies on continuous-space language models (e.g., Bengio et al. 2003; Mikolov et al. 2011; Schwenk et al., 2012), we use a neural network to project a word vector to a feature vector.”
SHEF-NN: Translation Quality Estimation with Neural Networks (2015, methodology): “For instance, neural network language models (Bengio et al., 2003) have been successfully explored in many problems including Automatic Speech Recognition (Schwenk and Gau-vain, 2005; Schwenk, 2007) and Machine Translation (Schwenk, 2012).”
Understanding of Machine Learning with Deep Learning: Architectures, Workflow, Applications and Future Directions (2023, background): “In 2012, Schwenk et al. [67] suggested a deep neural network-based phrase-based statistical machine translation system (DNN).”
Translation Modeling with Bidirectional Recurrent Neural Networks (2014, background): “Schwenk (2012) proposed a feedforward network that predicts phrases of a ﬁxed maximum length, such that all phrase words are predicted at once.”
Learning Bilingual Word Representations by Marginalizing Alignments (2014, background): “…et al. (2013), who learn a transformation matrix to reconcile monolingual embedding spaces, in an l 2 norm sense, using dictionary entries instead of alignments, as well as Schwenk et al. (2007) and Schwenk (2012), who also use distributed representations for estimating translation probabilities.”
On internal language representations in deep learning: an analysis of machine translation and speech recognition (2018, background): “Initially, they were incorporated in certain parts of previous statistical machine translation systems, such as language models [89, 298, 300], ordering models [86, 172, 206], or other components [218, 299].”
Neural Machine Translation (2020, unknown): “Moving beyond the use in language models, neural network methods crept into other components of traditional statistical machine translation, such as providing additional scores or extending translation tables (Schwenk, 2012; Lu et al., 2014), reordering (Kanouchi et al.”
Extraction of Salient Sentences from Labelled Documents (2014, background): “…the success of neural networks in many natural language processing domains such as language modelling (Mikolov et al., 2013), machine translation (Schwenk, 2012; Kalchbrenner & Blunsom, 2013a; Devlin et al., 2014; Cho et al., 2014; Bahdanau et al., 2014; Sutskever et al., 2014; Hermann &…”
Neural Machine Translation: A Review (2019, background): “, 2010), scoring phrase pairs directly with a feedforward net (Schwenk, 2012), or adding a source context window to the neural language model (Le et al.”