Recurrent neural network language model adaptation with curriculum learning

By Yangyang Shi, Martha A. Larson, C. Jonker. 2015

75 citations recorded by the source corpus.

Subfields: Artificial Intelligence

How researchers see this paper

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

In Artificial Intelligence

1. Loïc Barrault
2. Xiang Ren
3. Kyunghyun Cho
4. Mohit Bansal
5. Fethi Bougares
6. Yoshua Bengio
7. Graham Neubig
8. Xisen Jin

Citations in the corpus

• Incremental Adaptation Strategies for Neural Network Language Models (2014, background): “to adapt a recurrent LM to a sub-domain, again in the area of speech recognition (Shia et al., 2014).”
• Adversarial Domain Adaptation for Variational Neural Language Generation in Dialogue Systems (2018, background): “Recently, Recurrent Neural Networks (RNNs) based methods have shown improving results in tack-ling the domain adaptation issue (Chen et al., 2015; Shi et al., 2015; Wen et al., 2016a; Wen et al., 2016b).”
• Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora (2021, background): “We speculate the reason is that continual learning naturally provides a curriculum (Xu et al., 2020; Shi et al., 2015) to models where each individual task is easier to learn.”