当前位置: X-MOL 学术arXiv.cs.LG › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Fair Transfer of Multiple Style Attributes in Text
arXiv - CS - Machine Learning Pub Date : 2020-01-18 , DOI: arxiv-2001.06693
Karan Dabas, Nishtha Madan, Vijay Arya, Sameep Mehta, Gautam Singh, Tanmoy Chakraborty

To preserve anonymity and obfuscate their identity on online platforms users may morph their text and portray themselves as a different gender or demographic. Similarly, a chatbot may need to customize its communication style to improve engagement with its audience. This manner of changing the style of written text has gained significant attention in recent years. Yet these past research works largely cater to the transfer of single style attributes. The disadvantage of focusing on a single style alone is that this often results in target text where other existing style attributes behave unpredictably or are unfairly dominated by the new style. To counteract this behavior, it would be nice to have a style transfer mechanism that can transfer or control multiple styles simultaneously and fairly. Through such an approach, one could obtain obfuscated or written text incorporated with a desired degree of multiple soft styles such as female-quality, politeness, or formalness. In this work, we demonstrate that the transfer of multiple styles cannot be achieved by sequentially performing multiple single-style transfers. This is because each single style-transfer step often reverses or dominates over the style incorporated by a previous transfer step. We then propose a neural network architecture for fairly transferring multiple style attributes in a given text. We test our architecture on the Yelp data set to demonstrate our superior performance as compared to existing one-style transfer steps performed in a sequence.

中文翻译:

文本中多个样式属性的公平转移

为了保持匿名并在在线平台上混淆他们的身份,用户可能会改变他们的文本并将自己描绘成不同的性别或人口统计。同样,聊天机器人可能需要自定义其通信方式以提高与受众的参与度。这种改变书面文本风格的方式近年来受到了极大的关注。然而,这些过去的研究工作在很大程度上迎合了单一风格属性的转移。单独关注单一样式的缺点是,这通常会导致目标文本中其他现有样式属性的行为不可预测或被新样式不公平地支配。为了抵消这种行为,最好有一个风格转移机制,可以同时公平地转移或控制多种风格。通过这样的做法,人们可以获得模糊的或书面的文本,其中包含所需程度的多种软风格,例如女性品质、礼貌或正式。在这项工作中,我们证明了通过顺序执行多个单一风格转移无法实现多种风格的转移。这是因为每个单一的风格转移步骤通常会逆转或支配先前转移步骤所包含的风格。然后,我们提出了一种神经网络架构,用于在给定文本中公平地传输多个样式属性。我们在 Yelp 数据集上测试我们的架构,以证明与按顺序执行的现有单一式传输步骤相比,我们的卓越性能。我们证明了通过顺序执行多个单一风格转移无法实现多种风格的转移。这是因为每个单一的风格转移步骤通常会逆转或支配先前转移步骤所包含的风格。然后,我们提出了一种神经网络架构,用于在给定文本中公平地传输多个样式属性。我们在 Yelp 数据集上测试我们的架构,以证明与按顺序执行的现有单一式传输步骤相比,我们的卓越性能。我们证明了通过顺序执行多个单一风格转移无法实现多种风格的转移。这是因为每个单一的风格转移步骤通常会逆转或支配先前转移步骤所包含的风格。然后,我们提出了一种神经网络架构,用于在给定文本中公平地传输多个样式属性。我们在 Yelp 数据集上测试我们的架构,以证明与按顺序执行的现有单一式传输步骤相比,我们的卓越性能。然后,我们提出了一种神经网络架构,用于在给定文本中公平地传输多个样式属性。我们在 Yelp 数据集上测试我们的架构,以证明与按顺序执行的现有单一式传输步骤相比,我们的卓越性能。然后,我们提出了一种神经网络架构,用于在给定文本中公平地传输多个样式属性。我们在 Yelp 数据集上测试我们的架构,以证明与按顺序执行的现有单一式传输步骤相比,我们的卓越性能。
更新日期:2020-01-22
down
wechat
bug