scholarly journals Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph

2020 ◽  
Author(s):  
Haozhe Ji ◽  
Pei Ke ◽  
Shaohan Huang ◽  
Furu Wei ◽  
Xiaoyan Zhu ◽  
...  
Keyword(s):  
Knowledge Graph ◽  
Commonsense Knowledge ◽  
Language Generation

Iterative Visual Relationship Detection via Commonsense Knowledge Graph

2020 ◽  
pp. 210-225
Author(s):  
Hai Wan ◽  
Jialing Ou ◽  
Baoyi Wang ◽  
Jianfeng Du ◽  
Jeff Z. Pan ◽  
...  
Keyword(s):  
Knowledge Graph ◽  
Commonsense Knowledge

scholarly journals A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation

2020 ◽  
Vol 8 ◽  
pp. 93-108 ◽  
Author(s):  
Jian Guan ◽  
Fei Huang ◽  
Zhihao Zhao ◽  
Xiaoyan Zhu ◽  
Minlie Huang
Keyword(s):  
Long Range ◽  
Temporal Order ◽  
State Of The Art ◽  
Knowledge Bases ◽  
Fine Tuning ◽  
Causal Relationships ◽  
Commonsense Knowledge ◽  
Language Generation ◽  
Story Generation ◽  
Global Coherence

Story generation, namely, generating a reasonable story from a leading context, is an important but challenging task. In spite of the success in modeling fluency and local coherence, existing neural language generation models (e.g., GPT-2) still suffer from repetition, logic conflicts, and lack of long-range coherence in generated stories. We conjecture that this is because of the difficulty of associating relevant commonsense knowledge, understanding the causal relationships, and planning entities and events with proper temporal order. In this paper, we devise a knowledge-enhanced pretraining model for commonsense story generation. We propose to utilize commonsense knowledge from external knowledge bases to generate reasonable stories. To further capture the causal and temporal dependencies between the sentences in a reasonable story, we use multi-task learning, which combines a discriminative objective to distinguish true and fake stories during fine-tuning. Automatic and manual evaluation shows that our model can generate more reasonable stories than state-of-the-art baselines, particularly in terms of logic and global coherence.

scholarly journals Inductive Learning on Commonsense Knowledge Graph Completion

2021 ◽  
Author(s):  
Bin Wang ◽  
Guangtao Wang ◽  
Jing Huang ◽  
Jiaxuan You ◽  
Jure Leskovec ◽  
...  
Keyword(s):  
Inductive Learning ◽  
Knowledge Graph ◽  
Commonsense Knowledge

scholarly journals Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge Graph

2021 ◽  
Author(s):  
Rui Liu ◽  
Zheng Lin ◽  
Yutong Tan ◽  
Weiping Wang
Keyword(s):  
Knowledge Graph ◽  
Commonsense Knowledge

Diversified Paraphrase Generation with Commonsense Knowledge Graph

2021 ◽  
pp. 353-364
Author(s):  
Xinyao Shen ◽  
Jiangjie Chen ◽  
Yanghua Xiao
Keyword(s):  
Knowledge Graph ◽  
Commonsense Knowledge ◽  
Paraphrase Generation

Knowledge graph based natural language generation with adapted pointer-generator networks

2020 ◽  
Vol 382 ◽  
pp. 174-187 ◽  
Author(s):  
Weidong Li ◽  
Rong Peng ◽  
Yaqian Wang ◽  
Zhihuan Yan
Keyword(s):  
Natural Language ◽  
Natural Language Generation ◽  
Knowledge Graph ◽  
Language Generation

Iterative Visual Relationship Detection Via Commonsense Knowledge Graph

2020 ◽  
pp. 100175
Author(s):  
Hai Wan ◽  
Jinrui Liang ◽  
Jianfeng Du ◽  
Yanan Liu ◽  
Jialing Ou ◽  
...  
Keyword(s):  
Knowledge Graph ◽  
Commonsense Knowledge

scholarly journals Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Tasks

2020 ◽  
Author(s):  
Ting-Yun Chang ◽  
Yang Liu ◽  
Karthik Gopalakrishnan ◽  
Behnam Hedayatnia ◽  
Pei Zhou ◽  
...  
Keyword(s):  
Knowledge Graph ◽  
Commonsense Knowledge

scholarly journals Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations

2021 ◽  
Author(s):  
Tianqiao Liu ◽  
Qiang Fang ◽  
Wenbiao Ding ◽  
Hang Li ◽  
Zhongqin Wu ◽  
...  
Keyword(s):  
Word Problem ◽  
Knowledge Graph ◽  
Commonsense Knowledge ◽  
Problem Generation ◽  
Mathematical Word Problem
Sign in / Sign up

Export Citation Format

Share Document