Ensemble Learning for Multi-Source Neural Machine Translation

By Ekaterina Garmash, Christof Monz. 2016

102 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

Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer (2017, background): “Garmash & Monz (2016) suggest an ensemble model in the format of mixture of experts for machine translation.”
Beyond English-Centric Multilingual Machine Translation (2020, background): “We also tune a weight to balance the two language directions (Garmash and Monz, 2016).”
XNAS: Neural Architecture Search with Expert Advice (2019, background): “Mentions of Experts in deep learning [32, 52, 11, 1] literature go decades back [18, 5], typically combining models as separable experts sub-models.”
Search Engine Guided Non-Parametric Neural Machine Translation (2017, background): “…translation (Firat et al., 2016a; Luong et al., 2015; Dong et al., 2015), multi-source translation (Zoph and Knight, 2016; Firat et al., 2016b; Garmash and Monz, 2016), multimodal translation (Caglayan et al., 2016) and linguistic knowledge guided translation (Nadejde et al., 2017; Aharoni…”
Domain Adaptive Inference for Neural Machine Translation (2019, methodology): “During inference, Garmash and Monz (2016) use a gating network to learn weights for a multisource NMT ensemble.”
Unsupervised Quality Estimation for Neural Machine Translation (2020, methodology): “, 2019) and model ensemble (Garmash and Monz, 2016).”
Multilingual training for Software Engineering (2021, methodology): “Moreover, with tasks like summarization, or method naming, we are dealing with a simplified, many-to-one setting: translating multiple source languages to a single target language), which is believed to be easier than multi-way task [20, 76].”
A Survey of Multilingual Neural Machine Translation (2019, background): “Ensembling of individual source-target models is another beneﬁcial approach, for which Garmash and Monz (2016) proposed several methods with different degrees of parameterization.”
A Neural Model for Generating Natural Language Summaries of Program Subroutines (2019, methodology): “This is the same ensemble decoding procedure implemented by OpenNMT [59], and is one of the most common of several options described by literature on multi-source NMT [60].”
Multi-Source Neural Machine Translation with Missing Data (2018, methodology): “In this paper, we focus on this sort of multilingual scenario, specifically using multi-source translation [9]–[11].”
Enabling Multi-Source Neural Machine Translation By Concatenating Source Sentences In Multiple Languages (2017, methodology): “which uses separately trained single source models (Garmash and Monz, 2016) is comparatively simpler in the sense that one does not need to train additional NMT models but the approach is not truly end-to-end since it needs an ensemble func-”
Neural Machine Translation for Low-resource Languages: A Survey (2021, background): “(2) Translating from multiple source languages to a single target language (many-to-one) (Figure 4 (b)): This can be considered as a multi-source problem, and is relatively easier than the multi-task problem [61, 216].”
Automatic Document Sketching: Generating Drafts from Analogous Texts (2021, background): “multiple input documents (Liu and Lapata, 2019; Chu and Liu, 2019), and multi-source machine translation (Nishimura et al., 2018; Garmash and Monz, 2016) that encodes input texts in multiple source languages and translates them into a target”
Multi-Source Neural Machine Translation with Data Augmentation (2018, methodology): “There are two major approaches to multi-source NMT; multi-encoder NMT [10] and mixture of NMT Experts [11].”