arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1709.03010cs.CL
收藏

神经反应生成中的输出风格和主题导向

Steering Output Style and Topic in Neural Response Generation

Microsoft Research(微软研究院);Carnegie Mellon University(卡内基梅隆大学)

Di Wang, Nebojsa Jojic, Chris Brockett, Eric Nyberg

摘要:

我们提出了简单而灵活的训练和解码方法,以影响基于神经编码器-解码器的语言生成的输出风格和主题。这种能力在各种应用中都是理想的,包括会话系统,成功的代理需要以特定的风格产生语言,并生成由人类操纵者或外部知识操纵的响应。我们将神经生成过程分解为经验上更容易的子问题:忠诚度模型和基于选择性采样的解码方法。我们还描述了训练和采样算法,这些算法使用特定的语言风格限制或主题限制来偏置生成过程。人工评估结果表明,我们提出的方法能够限制风格和主题,而不会降低输出质量的会话任务。

英文摘要:

We propose simple and flexible training and decoding methods for influencing output style and topic in neural encoder-decoder based language generation. This capability is desirable in a variety of applications, including conversational systems, where successful agents need to produce language in a specific style and generate responses steered by a human puppeteer or external knowledge. We decompose the neural generation process into empirically easier sub-problems: a faithfulness model and a decoding method based on selective-sampling. We also describe training and sampling algorithms that bias the generation process with a specific language style restriction, or a topic restriction. Human evaluation results show that our proposed methods are able to restrict style and topic without degrading output quality in conversational tasks.

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。

↑