Fine-Tuning for Neural Machine Translation with Limited Degradation across In- and Out-of-Domain Data

By Praveen Dakwale, Christof Monz. 2017

53 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.

Citations in the corpus

Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation (2020, background): “Dakwale and Monz (2017) minimizes the cross-entropy between the output distribution of the general-domain model and the ﬁne-tuned model.”
Overcoming Catastrophic Forgetting During Domain Adaptation of Neural Machine Translation (2019, methodology): “We present the full trade-off for in- and generaldomain performance and show that our method outperforms MCL (Dakwale and Monz, 2017) at all operating points in five of six language pairs.”
Domain Adaptive Inference for Neural Machine Translation (2019, neutral): “, 2017) and fine-tuning output distributions (Dakwale and Monz, 2017; Khayrallah et al., 2018).”
Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation (2021, methodology): “We compare our method with the best capacity-fixed method EWC and best capacityincreased method MLL.”
Neural Machine Translation: A Review (2019, methodology): “Ghader and Monz (2017) provide a detailed analysis of how NMT uses attention to condition on the source sentence.”
A Survey of Domain Adaptation for Neural Machine Translation (2018, methodology): “On the other hand, the model centric category focuses on NMT models that are specialized for domain adaptation, which can be either the training objective (Luong and Manning, 2015; Sennrich et al., 2016b; Servan et al., 2016; Freitag and Al-Onaizan, 2016; Wang et al., 2017b; Chen et al., 2017a; Varg”
Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation (2018, methodology): “This ﬁnding may explain the recent success of techniques which regularize a continued training model using the initial, out-of-domain model (Miceli Barone et al., 2017; Dakwale and Monz, 2017; Khayrallah et al., 2018).”