Stanford Neural Machine Translation Systems for Spoken Language Domains

By Minh-Thang Luong, Christopher D. Manning. 2015

511 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

Multi-task Sequence to Sequence Learning (2015, methodology): “The early seq2seq work (Sutskever et al., 2014; Cho et al., 2014; Luong et al., 2015b; Vinyals et al., 2015b) uses only the last encoder state to initialize the decoder and sets s = [ ] in Eq.”
Improving Neural Machine Translation Models with Monolingual Data (2015, methodology): “Future work will explore the effectiveness of our approach in more settings.”
Simple, Scalable Adaptation for Neural Machine Translation (2019, methodology): “approach for adapting to new domains and languages (Luong and Manning, 2015; Neubig and Hu, 2018).”
What do Neural Machine Translation Models Learn about Morphology? (2017, background): “The improved translation quality is often attributed to better handling of non-local dependencies and morphology generation (Luong 1Our code is available at https://github.com/ boknilev/nmt-repr-analysis. and Manning, 2015; Bentivogli et al., 2016; Toral and Sánchez-Cartagena, 2017).”
Six Challenges for Neural Machine Translation (2017, background): “A currently popular approach is to train a general domain system, followed by training on in-domain data for a few epochs (Luong and Manning, 2015; Freitag and Al-Onaizan, 2016).”
Data Noising as Smoothing in Neural Network Language Models (2017, methodology): “Following Luong & Manning (2015), we use TED tst2012 as a validation set and report BLEU score results (Papineni et al., 2002) on tst2014.”
Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation (2022, positive): “transfer the out-domain knowledge to in-domain (Luong and Manning, 2015b).”
Continual Learning for Neural Machine Translation (2021, methodology): “To improve the performance of NMT models in low-resource domains, a widely-used technique is to train the model on a general domain corpus, and then ﬁne-tune it on the in-domain corpus via continual training (Sennrich et al., 2016; Luong and Manning, 2015).”
Continual Lifelong Learning in Natural Language Processing: A Survey (2020, positive): “The approach introduced by Luong and Manning (2015) laid the groundwork for subsequent studies in adapting neural machine translation (NMT).”
Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation (2020, background): “Luong and Manning (2015) ﬁne tunes the general-domain model with the in-domain data.”
Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models (2016, background): “NMT has already achieved state-of-the-art translation results for several language pairs such as English-French (Luong et al., 2015b), English-German (Jean et al., 2015a; Luong et al., 2015a; Luong and Manning, 2015), and English-Czech (Jean et al., 2015b).”
Online and Linear-Time Attention by Enforcing Monotonic Alignments (2017, methodology): “Typically, a(·) is a single-layer neural network using a tanh nonlinearity, but other functions such as a simple dot product between si−1 and hj have been used (Luong et al., 2015; Graves et al., 2014).”
Fast Domain Adaptation for Neural Machine Translation (2016, methodology): “For neural machine translation, [Luong and Manning, 2015] proposed to adapt an already existing NMT system to a new domain with further training on the in-domain data only.”
Controlling Politeness in Neural Machine Translation via Side Constraints (2016, background): “Attentional neural machine translation (Bahdanau et al., 2015) is the current state of the art for English → German (Jean et al., 2015b; Luong and Manning, 2015).”
Overcoming Catastrophic Forgetting During Domain Adaptation of Neural Machine Translation (2019, background): “Continued training (Luong and Manning, 2015; Sennrich et al., 2015) (also called fine-tuning), where a model is first trained on general-domain data and then domain adapted by training on in-domain data, is a popular approach in this setting as it leads to empirical improvements in the targeted doma”