Papers with knowledge graph-to-text

2 papers
Bi-Directional Multi-Granularity Generation Framework for Knowledge Graph-to-Text with Large Language Model (2024.acl-short)

Copied to clipboard

Challenge: Existing methods generate whole text based on all KG triples at once and may incorporate incorrect KG Triples for each sentence.
Approach: They propose a bi-directional multi-granularity generation framework that generates graph-level sentences based on KG triples instead of the whole text at a time.
Outcome: The proposed framework achieves state-of-the-art in benchmark dataset WebNLG and further analysis shows the efficiency of different modules.
Structure-aware Knowledge Graph-to-text Generation with Planning Selection and Similarity Distinction (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods to generate knowledge graph-to-text (KG-to) text rely on pre-trained language models to bridge the gap between the different structures of the input KG and the target text.
Approach: They propose a method that integrates graph structure-aware modules with pre-trained language models to capture the intricate topology information present in the KG.
Outcome: The proposed model captures the topology information present in the knowledge graph and distinguishes similar input KGs through contrastive learning techniques.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations