UvA-DARE ( Digital Academic Repository ) Latent Domain Translation Models in Mix-of-Domains Haystack
By Cuong Hoang, Khalil Sima'an. 2014
Subfields: Natural Language Processing, Representation & Self-Supervised Learning
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
- Philipp Koehn
- Ondrej Bojar
- Lucia Specia
- Christof Monz
- Barry Haddow
- Graham Neubig
- Yvette Graham
- Matt Post
In Representation & Self-Supervised Learning
- Chenhui Chu
- Rui Wang
- Philipp Koehn
- Marianna J. Martindale
- Yogarshi Vyas
- Amittai Axelrod
- Stella Frank
- Barry Haddow
Citations in the corpus
- Findings of the 2016 Conference on Machine Translation (2016, background): “IILC-UVA-DS is based on Hoang and Sima’an (2014).”
- Class-based N-gram language difference models for data selection (2015, methodology): “Furthermore, [6] showed improvements by using EM to identify true out-of-domain data from the pool to contrast against the in-domain data.”
- A Survey of Domain Adaptation for Neural Machine Translation (2018, methodology): “LMs (Moore and Lewis, 2010; Axelrod et al., 2011; Duh et al., 2013), as well as joint models (Hoang and Sima’an, 2014; Durrani et al., 2015), and more recently convolutional neural network (CNN) models (Chen et al., 2016) can be used to score sentences. ii) When there are not enough parallel…”
- ILLC-UvA Adaptation System (Scorpio) at WMT’16 IT-DOMAIN Task (2016, methodology): “We use simple latent domain variable model for adaptation proposed in (Cuong and Sima’an, 2014b; Cuong and Sima’an, 2014a).”