arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.03535cs.CLcs.LGcs.NE
收藏

CoCon:一种自监督的受控文本生成方法

CoCon: A Self-Supervised Approach for Controlled Text Generation

Nanyang Technological University(南洋理工大学);Amazon AI(亚马逊人工智能);Mila(米拉研究所);Polytechnique Montreal(蒙特利尔理工学院)

Alvin Chan, Yew-Soon Ong, Bill Pung, Aston Zhang, Jie Fu

摘要:

预训练的基于transformer的语言模型(LM)显示出卓越的自然语言生成能力。由于其巨大的潜力,控制这种LM的文本生成越来越受到关注。虽然有一些研究试图控制生成文本的高级属性(如情感和主题),但仍然缺乏对单词和短语级别的内容进行更精确的控制。在这里,我们建议内容调节器(CoCon)控制LM的输出文本与内容输入,在细粒度的水平。在我们的自我监督方法中,CoCon块通过调节LM保留的内容输入来学习帮助LM完成部分观察到的文本序列。通过实验,我们表明,CoCon可以自然地将目标内容纳入生成的文本和控制高层次的文本属性在一个zero-shot的方式。

英文摘要:

Pretrained Transformer-based language models (LMs) display remarkable natural language generation capabilities. With their immense potential, controlling text generation of such LMs is getting attention. While there are studies that seek to control high-level attributes (such as sentiment and topic) of generated text, there is still a lack of more precise control over its content at the word- and phrase-level. Here, we propose Content-Conditioner (CoCon) to control an LM's output text with a content input, at a fine-grained level. In our self-supervised approach, the CoCon block learns to help the LM complete a partially-observed text sequence by conditioning with content inputs that are withheld from the LM. Through experiments, we show that CoCon can naturally incorporate target content into generated texts and control high-level text attributes in a zero-shot manner.

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。

↑