Timezone: »

Unsupervised Text Generation by Learning from Search
Jingjing Li · Zichao Li · Lili Mou · Xin Jiang · Michael Lyu · Irwin King

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #982

In this work, we propose TGLS, a novel framework for 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, unsupervised paraphrasing and text formalization. Our model significantly outperforms unsupervised baseline methods in both tasks. Especially, it achieves comparable performance to strong supervised methods for paraphrase generation.

Author Information

Jingjing Li (The Chinese University of Hong Kong)
Zichao Li (Huawei Noah's Ark Lab)
Lili Mou (University of Alberta)
Xin Jiang (Huawei Noah's Ark Lab)
Michael Lyu (CUHK)
Irwin King (Chinese University of Hong Kong)

More from the Same Authors