Papers › Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network
Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network
Deming Ye, Yankai Lin, Zheng-Hao Liu, Zhiyuan Liu, Maosong Sun
Multi-paragraph reasoning is indispensable for open-domain question answering (OpenQA), which receives less attention in the current OpenQA systems. In this work, we propose a knowledge-enhanced graph neural network (KGNN), which performs reasoning over multiple paragraphs with entities. To explicitly capture the entities' relatedness, KGNN utilizes relational facts in knowledge graph to build the entity graph. The experimental results show that KGNN outperforms in both distractor and full wiki settings than baselines methods on HotpotQA dataset. And our further analysis illustrates KGNN is effective and robust with more retrieved paragraphs.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Question Answering | HotpotQA | KGNN | ANS-EM | 0.277 | #58 of 72 | Archive leaderboard | report |
| Question Answering | HotpotQA | KGNN | ANS-F1 | 0.372 | #58 of 72 | Archive leaderboard | report |
| Question Answering | HotpotQA | KGNN | JOINT-EM | 0.070 | #58 of 72 | Archive leaderboard | report |
| Question Answering | HotpotQA | KGNN | JOINT-F1 | 0.247 | #58 of 72 | Archive leaderboard | report |
| Question Answering | HotpotQA | KGNN | SUP-EM | 0.127 | #58 of 72 | Archive leaderboard | report |
| Question Answering | HotpotQA | KGNN | SUP-F1 | 0.472 | #58 of 72 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections