论文标题
通过从搜索中学习而无监督的文本生成
Unsupervised Text Generation by Learning from Search
论文作者
论文摘要
在这项工作中，我们提出了TGLS，这是一种通过从搜索中学习来无监督文本生成的新颖框架。我们首先将强大的搜索算法（特别是模拟退火）应用于启发式定义的目标，该目标（大致）估计句子的质量。然后，有条件的生成模型从搜索结果中学习，同时平滑搜索的噪音。可以重复搜索和学习之间的交替以进行性能引导。我们证明了TGL对两个现实世界的自然语言生成任务，释义生成和文本形式化的有效性。我们的模型在这两个任务中都大大优于无监督的基线方法。尤其是，它通过释义生成的最新监督方法实现了可比的性能。
In this work, we present TGLS, a novel framework to unsupervised Text Generation by Learning from Search. We start by applying a strong search algorithm (in particular, simulated annealing) towards a heuristically defined objective that (roughly) estimates the quality of sentences. Then, a conditional generative model learns from the search results, and meanwhile smooth out the noise of search. The alternation between search and learning can be repeated for performance bootstrapping. We demonstrate the effectiveness of TGLS on two real-world natural language generation tasks, paraphrase generation and text formalization. Our model significantly outperforms unsupervised baseline methods in both tasks. Especially, it achieves comparable performance with the state-of-the-art supervised methods in paraphrase generation.
