SHAPED：用于文本样式自适应的共享私有编码器-解码器
SHAPED: Shared-Private Encoder-Decoder for Text Style Adaptation
摘要：
抽象语言生成模型的监督训练导致基于监督训练信号学习语言序列上的条件概率。当训练信号包含各种书写风格时，这样的模型可能最终学习直接受训练数据组成影响并且不能由应用的需要控制的“平均”风格。我们描述了一个家庭的模型架构，能够捕捉通用的语言特征，通过共享的模型参数，以及特定的风格特征，通过私人模型参数。这样的模型能够根据特定的学习风格生成语言，同时仍然利用它们的能力来建模通用语言现象。此外，我们描述了一个扩展，它使用所有学习到的样式的输出分布的混合物来执行仅基于文本输入的动态样式适应。实验上，我们发现，所提出的模型始终优于封装单一风格或平均风格的语言生成能力的模型。
英文摘要：
Supervised training of abstractive language generation models results in learning conditional probabilities over language sequences based on the supervised training signal. When the training signal contains a variety of writing styles, such models may end up learning an 'average' style that is directly influenced by the training data make-up and cannot be controlled by the needs of an application. We describe a family of model architectures capable of capturing both generic language characteristics via shared model parameters, as well as particular style characteristics via private model parameters. Such models are able to generate language according to a specific learned style, while still taking advantage of their power to model generic language phenomena. Furthermore, we describe an extension that uses a mixture of output distributions from all learned styles to perform on-the fly style adaptation based on the textual input alone. Experimentally, we find that the proposed models consistently outperform models that encapsulate single-style or average-style language generation capabilities.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
