IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation

Autor:	Jin, Zhijing, Jin, Di, Mueller, Jonas, Matthews, Nicholas, Santus, Enrico
Rok vydání:	2019
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Text attribute transfer aims to automatically rewrite sentences such that they possess certain linguistic attributes, while simultaneously preserving their semantic content. This task remains challenging due to a lack of supervised parallel data. Existing approaches try to explicitly disentangle content and attribute information, but this is difficult and often results in poor content-preservation and ungrammaticality. In contrast, we propose a simpler approach, Iterative Matching and Translation (IMaT), which: (1) constructs a pseudo-parallel corpus by aligning a subset of semantically similar sentences from the source and the target corpora; (2) applies a standard sequence-to-sequence model to learn the attribute transfer; (3) iteratively improves the learned transfer function by refining imperfections in the alignment. In sentiment modification and formality transfer tasks, our method outperforms complex state-of-the-art systems by a large margin. As an auxiliary contribution, we produce a publicly-available test set with human-generated transfer references. Comment: EMNLP 2019 (Long Paper)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1901.11333 Zobrazit plný text záznamu View this record from Arxiv