Deep Copycat Networks for Text-to-Text Generation

Julia Ive, Pranava Madhyastha, Lucia Specia
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
Most text-to-text generation tasks, for example text summarisation and text simplification, require copying words from the input to the output. We introduce copycat, a transformerbased pointer network for such tasks which obtains competitive results in abstractive text summarisation and generates more abstractive summaries. We propose a further extension of this architecture for automatic post-editing, where generation is conditioned over two inputs (source language and machine translation),
more » ... the model is capable of deciding where to copy information from. This approach achieves competitive performance when compared to state-of-the-art automated post-editing systems. More importantly, we show that it addresses a well-known limitation of automatic post-editing -overcorrecting translations -and that our novel mechanism for copying source language words improves the results.
doi:10.18653/v1/d19-1318 dblp:conf/emnlp/IveMS19 fatcat:c7yvvpe7wbfbhpiaz3kx55ggku