Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review

J Chen, Y Xiao - arXiv preprint arXiv:2212.03747, 2022 - arxiv.org
The rapid development and application of natural language generation (NLG) techniques
has revolutionized the field of automatic text production. However, these techniques are still …

Generative entity typing with curriculum learning

S Yuan, D Yang, J Liang, Z Li, J Liu, J Huang… - arXiv preprint arXiv …, 2022 - arxiv.org
Entity typing aims to assign types to the entity mentions in given texts. The traditional
classification-based entity typing paradigm has two unignorable drawbacks: 1) it fails to …

Towards fine-grained concept generation

C Li, J Liang, Y Xiao, H Jiang - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Constructing large-scale taxonomies are crucial for many knowledge-rich applications that
need concepts to better understand texts. However, current taxonomies suffer from the …