Context-Dependent Translation Selection Using Convolutional Neural Network
By Baotian Hu, Zhaopeng Tu, Zhengdong Lu, Hang Li, Qingcai Chen. 2015
27 citations recorded by the source corpus.
We propose a novel method for translation selection in statistical machine translation, in which a convolutional neural network is employed to judge the similarity between a phrase pair in two languages. The specifically designed convolutional architecture encodes not only the semantic similarity of the translation pair, but also the context containing the phrase in the source language. Therefore, our approach is able to capture context-dependent semantic similarities of translation pairs. We adopt a curriculum learning strategy to train the model: we classify the training examples into easy, medium, and difficult categories, and gradually build the ability of representing phrase and sentence level context by using training examples from easy to difficult. Experimental results show that our approach significantly outperforms the baseline system by up to 1.4 BLEU points.
Subfields: Artificial Intelligence, Molecular Biology, Natural Language Processing
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
- Erik Cambria
- Soujanya Poria
- Devamanyu Hazarika
- Percy Liang
- Michael Auli
- Myle Ott
- David Grangier
- Tom Young
In Molecular Biology
- Hyoungseop Kim
- Soujanya Poria
- Seiichi Serikawa
- Tom Young
- Min Chen
- Michael Auli
- David Grangier
- Yann Dauphin
In Natural Language Processing
- Michael Auli
- David Grangier
- Yann Dauphin
- Myle Ott
- Erik Cambria
- Soujanya Poria
- Devamanyu Hazarika
- Angela Fan
Citations in the corpus
- A Convolutional Encoder Model for Neural Machine Translation (2016, background): “(2015) and (Tu et al., 2015) applied convolutional models to score phrase-pairs of traditional phrasebased and dependency-based translation models.”
- Recent Trends in Deep Learning Based Natural Language Processing (2017, methodology): “Nevertheless, [62] addressed this task by considering both the semantic similarity of the translation pair and their respective contexts.”
- Recent Trends in Deep Learning Based Natural Language Processing [Review Article] (2018, methodology): “[61] extended the work of Chen and Manning [129] by employing a deeper model with 2 hidden layers.”
- Brain Intelligence: Go beyond Artificial Intelligence (2017, methodology): “Convolutional neural networks (CNN) [43] are similar to traditional neural networks (NN).”