A Deep Neural Network Approach To Parallel Sentence Extraction
This work addresses the data sparsity problem in multilingual NLP applications, offering a novel deep learning solution for parallel sentence extraction, which is incremental in applying existing deep learning techniques to this specific task.
The authors tackled the problem of parallel sentence extraction for multilingual NLP by proposing an end-to-end deep neural network that uses continuous sentence representations, eliminating the need for domain-specific feature engineering. Their approach, based on siamese bidirectional RNNs, significantly improved both the quality of extracted sentences and the translation performance of statistical machine translation systems compared to a strong baseline.
Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose an end-to-end deep neural network approach to detect translational equivalence between sentences in two different languages. In contrast to previous approaches, which typically rely on multiples models and various word alignment features, by leveraging continuous vector representation of sentences we remove the need of any domain specific feature engineering. Using a siamese bidirectional recurrent neural networks, our results against a strong baseline based on a state-of-the-art parallel sentence extraction system show a significant improvement in both the quality of the extracted parallel sentences and the translation performance of statistical machine translation systems. We believe this study is the first one to investigate deep learning for the parallel sentence extraction task.