Text Generation

Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review
We briefly review the recent progress of knowledge-guided NLG, sets ten goals for future development, and envisions challenges in attaining these objectives.
Jiangjie Chen, Yanghua Xiao
PDF
Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review
Converge to the Truth: Factual Error Correction via Iterative Constrained Editing
Fact verification guided iterative factual error correction without the supervision from corretion.
Jiangjie Chen, Rui Xu, Wenxuan Zeng, Changzhi Sun, Lei Li, Yanghua Xiao
PDF Cite Code Poster Slides DOI
Converge to the Truth: Factual Error Correction via Iterative Constrained Editing
Unsupervised Explanation Generation via Correct Instantiations
Generate explanations for why a statement is wrong by prompting LLMs with the correct version of it.
Sijie Cheng, Zhiyong Wu, Jiangjie Chen, Zhixing Li, Yang Liu, Lingpeng Kong
PDF Cite Code Poster Slides DOI
Unsupervised Explanation Generation via Correct Instantiations
Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints
We present ACT, an algorithm that enhances non-autoregressive translation (NAT) by improving constraint preservation and translation quality, especially for rare constraints.
Chun Zeng, Jiangjie Chen, Tianyi Zhuang, Rui Xu, Hao Yang, Ying Qin, Shimin Tao, Yanghua Xiao
PDF Cite Code Slides Video DOI
Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints
Theme II - Towards Factual, Controllable and Versatile Text Generation 🤖
The success of deep text generation is being held back by its non-factuality. How to unleash the power of text generation models while restraining them from talking gibberish? Perhaps the first step is the identification of non-factuality.
Feb 27, 2022
FalCon: A Faithful Contrastive Framework for Response Generation in TableQA Systems
In a practical TableQA system, response generation is a critical module to generate a natural language description of the SQL and the …
Shineng Fang, Jiangjie Chen, Xinyao Shen, Yunwen Chen, Yanghua Xiao
PDF Cite Code DOI
FalCon: A Faithful Contrastive Framework for Response Generation in TableQA Systems
Unsupervised Editing for Counterfactual Stories
Creating counterfactual story endings (what-if stories) with unsupervised editing.
Jiangjie Chen, Chun Gan, Sijie Cheng, Hao Zhou, Yanghua Xiao, Lei Li
PDF Cite Code Poster Slides Video DOI
Unsupervised Editing for Counterfactual Stories
Diversified Query Generation Guided with Knowledge Graph
Relevant articles recommendation plays an important role in online news platforms. Directly displaying recalled articles by a search …
Xinyao Shen, Jiangjie Chen, Jiaze Chen, Chun Zeng, Yanghua Xiao
PDF Cite Code Slides DOI
Diversified Query Generation Guided with Knowledge Graph
Diversified Paraphrase Generation with Commonsense Knowledge Graph
Paraphrases refer to text with different expressions conveying the same meaning, which is usually modeled as a sequence-to-sequence …
Xinyao Shen, Jiangjie Chen, Yanghua Xiao
PDF Cite DOI
Ensuring Readability and Data-fidelity using Head-modifier Templates in Deep Type Description Generation
Building head-modifier templates to constrain entity type description generation.
Jiangjie Chen, Ao Wang, Haiyun Jiang, Suo Feng, Chenguang Li, Yanghua Xiao
PDF Cite Code Poster DOI
Ensuring Readability and Data-fidelity using Head-modifier Templates in Deep Type Description Generation