paper-with-me

Papers

Unsupervised Text Generation by Learning from Search

2020-07-09 · NeurIPS 2020 12 · Jingjing Li, Zichao Li, Lili Mou, Xin Jiang, Michael R. Lyu, Irwin King

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.

📄 PDF Abstract BibTeX arXiv:2007.08557

Code (0)

등록된 구현이 없습니다.

Tasks

Paraphrase GenerationText Generation

Similar Papers 제목 키워드 기반

GenWiki: A Dataset of 1.3 Million Content-Sharing Text and Graphs for Unsupervised Graph-to-Text Generation

2020-12-01 · COLING 2020 8 · Zhijing Jin, Qipeng Guo, Xipeng Qiu, Zheng Zhang

Data collection for the knowledge graph-to-text generation is expensive. As a result, research on unsupervised models has emerged as an active field recently. However, most unsupervised models have to use non-parallel ve…

Knowledge GraphsText GenerationUnsupervised KG-to-Text Generation

Effective Unsupervised Constrained Text Generation based on Perturbed Masking

2024-04-24 · Findings (ACL) 2022 5 · Yingwen Fu, Wenjie Ou, Zhou Yu, Yue Lin

Unsupervised constrained text generation aims to generate text under a given set of constraints without any supervised data. Current state-of-the-art methods stochastically sample edit positions and actions, which may ca…

PositionSentenceText Generation

Effective Unsupervised Constrained Text Generation based on Perturbed Masking

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Unsupervised constrained text generation aims to generate text under a given set of constraints without any supervised data. Current state-of-the-art methods stochastically sample edit positions which may cause unnecessa…

PositionSentenceText Generation

Search and Learning for Unsupervised Text Generation

2023-09-18 · Lili Mou

With the advances of deep learning techniques, text generation is attracting increasing interest in the artificial intelligence (AI) community, because of its wide applications and because it is an essential component of…

SentenceText Generation

Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Text summarization aims to generate a short summary for an input text. In this work, we propose a Non-Autoregressive Unsupervised Summarization (NAUS) approach, which does not require parallel data for training. Our NAUS…

Headline GenerationSentenceSentence SummarizationText Summarization+1