KENLG-Reading  by wyu97

Reading list for knowledge-enhanced text generation, with a survey

created 4 years ago
521 stars

Top 61.3% on sourcepulse

GitHubView on GitHub
Project Summary

This repository provides a curated list of resources for knowledge-enhanced text generation, targeting researchers and practitioners in Natural Language Generation (NLG). It offers a comprehensive survey paper, tutorials, and categorized links to papers, code, and datasets, serving as a valuable starting point for understanding and advancing the field.

How It Works

The repository is structured around a survey paper that categorizes knowledge-enhanced text generation techniques. It then links to relevant research papers and their associated code, covering various approaches such as knowledge graph integration, retrieval augmentation, and controllable generation methods. This organization allows users to explore specific sub-fields and access foundational and state-of-the-art resources.

Quick Start & Requirements

This repository is a curated list of resources and does not have a direct installation or execution command. Users will need to follow individual links to access papers, code repositories, and datasets, which may have their own specific setup requirements (e.g., Python, PyTorch, TensorFlow, specific hardware).

Highlighted Details

  • Features a comprehensive survey paper published in ACM CSUR (2022).
  • Includes links to tutorials from major NLP conferences (EMNLP 2021, ACL 2022).
  • Organizes resources by knowledge integration type (knowledge base, knowledge graph, retrieval, topic, keyword) and task (dialogue, summarization, QA, etc.).
  • Marks papers with available code ( ) and high recent citations ( ).

Maintenance & Community

The repository is contributed to by Wenhao Yu and Qingyun Wang, with the last update noted on February 5th, 2022. Users are encouraged to open issues or pull requests for errors or additions.

Licensing & Compatibility

The repository itself does not specify a license. Individual linked papers and code repositories will have their own licenses, which may vary and could include restrictions on commercial use or derivative works.

Limitations & Caveats

The content was last updated in February 2022, meaning it may not include the latest advancements in the rapidly evolving field of knowledge-enhanced text generation. Users must consult the licenses of individual linked resources for usage permissions.

Health Check
Last commit

3 years ago

Responsiveness

1 day

Pull Requests (30d)
0
Issues (30d)
0
Star History
1 stars in the last 90 days

Explore Similar Projects

Feedback? Help us improve.