Continuous Space Translation Models with Neural Networks

By Hang Le, Alexander Allauzen, François Yvon. 2012

150 citations recorded by the source corpus.

Subfields: Model Architectures, Machine Translation

How researchers see this paper

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

In Model Architectures

In Machine Translation

Citations in the corpus

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation (2014, neutral): “See, e.g., (Schwenk, 2012), (Son et al., 2012) and (Zou et al., 2013).”
Addressing the Rare Word Problem in Neural Machine Translation (2014, methodology): “…used a large and deep Long Short-Term Memory (LSTM) model, Cho et al. [5] used an architecture similar to the LSTM, and Bahdanau et al. [2] used a more elaborate neural network architecture that uses an attentional mechanism over the input sequence, similarly to Graves [9] and Graves et al. [10].”
Sequence-to-sequence neural net models for grapheme-to-phoneme conversion (2015, positive): “In recent work on sequence to sequence translation, it has been shown that side-conditioned neural networks can be effectively used for both machine translation [1–6] and image captioning [7–10].”
Learning Continuous Phrase Representations for Translation Modeling (2014, methodology): “This follows the common smoothing strategy of addressing the data sparseness problem in modeling phrase translations, such as the lexical weighting model (Koehn et al. 2003) and the word factored n-gram translation model (Son et al. 2012).”
Bilingual Word Embeddings for Phrase-Based Machine Translation (2013, methodology): “Only recently have continuous space models been applied to machine translation (Le et al., 2012).”
Incremental Adaptation Strategies for Neural Network Language Models (2014, methodology): “tion model in an SMT system (Le et al., 2012; Schwenk, 2012; Cho et al., 2014), and first translations systems entirely based on neural networks were proposed (Sutskever et al.”
Translation Modeling with Bidirectional Recurrent Neural Networks (2014, methodology): “To the best of our knowledge, the earliest attempts to apply neural networks in machine translation (MT) are presented in (Casta˜no et al., 1997; Casta˜no and Casacuberta, 1997; Casta˜no and Casacuberta, 1999), where they were used for example-based MT. Recently, Le et al. (2012) presented translati”
Recurrent Neural Networks for Word Alignment Model (2014, methodology): “Recently, FFNNs have been applied successfully to several tasks, such as speech recognition (Dahl et al., 2012), statistical machine translation (Le et al., 2012; Vaswani et al., 2013), and other popular natural language processing tasks (Collobert and Weston, 2008; Col-lobert et al., 2011).”
The KIT-LIMSI Translation System for WMT 2014 (2014, methodology): “The SOUL models used for this year’s evaluation are similar to those described in Allauzen et al. (2013) and Le et al. (2012b).”
Continuous Space Translation Models for Phrase-Based Statistical Machine Translation (2012, methodology): “Previous works on continuous space translation models in an bilingual tuple system only used rescoring (Schwenk et al., 2007; Le et al., 2012).”
Investigating the Usefulness of Generalized Word Representations in SMT (2014, background): “More recent research has started to set apart from the conventional maximum likelihood estimates toward neural network-based models that use continuous space representation (Schwenk, 2012; Le et al., 2012; Hu et al., 2014; Gao et al., 2014).”
The KIT-LIMSI Translation System for WMT 2015 (2015, methodology): “While the CTMs under study in this paper were initially introduced within the framework of n -gram-based systems (Le et al., 2012), they could be used with any phrase-based system.”