Research map / Graph learning / Knowledge and temporal graphs
Capturing Sentence Relations for Answer Sentence Selection with Multi-Perspective Graph Encoding
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add MPGE candidate-relation encoder (ablation) | BERT answer selector · WikiQA | MAP: 83.4 -> 86.7 | Helped |
| add MPGE (ablation) | traditional representation selector · WikiQA | MAP: 72.1 -> 77.3 | Helped |
| add MPGE (ablation) | BERT answer selector · SQuAD | MAP: 93.3 -> 95.0 | Helped |
| add MPGE (ablation) | BERT answer selector · SQuAD AddSent | MAP: 73.8 -> 78.4 | Helped |
| add dynamic graph (ablation) | TR-MPGE-AS · WikiQA | MAP: 75.4 -> 77.3 | Helped |
| add entity graph (ablation) | TR-MPGE-AS · WikiQA | MAP: 76.3 -> 77.3 | Helped |
| add distance graph (ablation) | BR-MPGE-AS · WikiQA | MAP: 85.8 -> 86.7 | Helped |
| add similarity graph (ablation) | BR-MPGE-AS · WikiQA | MAP: 86.2 -> 86.7 | Helped |
| use BiGRU fusion instead of linear fusion (ablation) | TR-MPGE-AS · WikiQA | MAP: 76.9 -> 77.3 | Helped |
| use BiGRU fusion instead of linear fusion (ablation) | BR-MPGE-AS · WikiQA | MAP: 86.5 -> 86.7 | Helped |
| use MPGE instead of sentence-level BiGRU (ablation) | BERT answer selector · WikiQA | MAP: 84.0 -> 86.7 | Helped |
| use sentence-level BiGRU over candidates instead of none (ablation) | BERT answer selector · WikiQA | MAP: 83.4 -> 84.0 | Helped |
Closest papers by meaning
- Hybrid Attentive Answer Selection in CQA With Deep Users Modelling (AAAI 2018 · similarity 0.86)
- A Question-Focused Multi-Factor Attention Network for Question Answering (AAAI 2018 · similarity 0.86)
- Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation (ICLR 2020 · similarity 0.85)
- Relation-Aware Language-Graph Transformer for Question Answering (AAAI 2023 · similarity 0.85)
- G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering (NeurIPS 2024 · similarity 0.84)
- Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation (AAAI 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.