%0 Conference Proceedings %T Adversarial Decomposition of Text Representation %A Romanov, Alexey %A Rumshisky, Anna %A Rogers, Anna %A Donahue, David %Y Burstein, Jill %Y Doran, Christy %Y Solorio, Thamar %S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) %D 2019 %8 June %I Association for Computational Linguistics %C Minneapolis, Minnesota %F romanov-etal-2019-adversarial %X In this paper, we present a method for adversarial decomposition of text representation. This method can be used to decompose a representation of an input sentence into several independent vectors, each of them responsible for a specific aspect of the input sentence. We evaluate the proposed method on two case studies: the conversion between different social registers and diachronic language change. We show that the proposed method is capable of fine-grained controlled change of these aspects of the input sentence. It is also learning a continuous (rather than categorical) representation of the style of the sentence, which is more linguistically realistic. The model uses adversarial-motivational training and includes a special motivational loss, which acts opposite to the discriminator and encourages a better decomposition. Furthermore, we evaluate the obtained meaning embeddings on a downstream task of paraphrase detection and show that they significantly outperform the embeddings of a regular autoencoder. %R 10.18653/v1/N19-1088 %U https://aclanthology.org/N19-1088 %U https://doi.org/10.18653/v1/N19-1088 %P 815-825