Research map / Graph learning / Knowledge and temporal graphs
Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks
Pavan Kapanipathi, Veronika Thost, Siva Sankalp Patel, Spencer Whitehead, Ibrahim Abdelaziz, Avinash Balakrishnan, Maria Chang, Kshitij Fadnis, Chulaka Gunasekara, Bassem Makni, Nicholas Mattei, Kartik Talamadupula and 1 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 ConceptNet subgraph features to BERT+match-LSTM | BERT+match-LSTM · SciTail | accuracy: 89.13 -> 90.68 | Improved |
| Add ConceptNet subgraph features to BERT+match-LSTM | BERT+match-LSTM · MultiNLI | accuracy: 77.96 -> 76.73 | Hurt |
| Add ConceptNet subgraph features to BERT+match-LSTM | BERT+match-LSTM · SNLI | accuracy: 85.78 -> 85.97 | Improved |
| Add ConceptNet subgraph features to match-LSTM | match-LSTM · BreakingNLI | accuracy: 65.11 -> 78.72 | Improved |
| Add ConceptNet subgraph features to BERT+match-LSTM | BERT+match-LSTM · BreakingNLI | accuracy: 59.42 -> 77.59 | Improved |
| Add ConceptNet subgraph features to HBMP | HBMP · BreakingNLI | accuracy: 60.31 -> 63.60 | Improved |
| Add ConceptNet subgraph features to DecompAttn | DecompAttn · SciTail | accuracy: 76.57 -> 72.43 | Hurt |
| Add ConceptNet subgraph features to DecompAttn | DecompAttn · SNLI | accuracy: 79.28 -> 85.56 | Improved |
| Add ConceptNet subgraph features to ConSeqNet-style text model | ConSeqNet · BreakingNLI | accuracy: 65.11 -> 61.12 | Hurt |
Closest papers by meaning
- Select and Augment: Enhanced Dense Retrieval Knowledge Graph Augmentation (Abstract Reprint) (AAAI 2024 · similarity 0.87)
- Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models (NeurIPS 2025 · similarity 0.85)
- Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation (AAAI 2025 · similarity 0.85)
- Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven Optimization (AAAI 2025 · similarity 0.85)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.84)
- Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation (ICLR 2025 · similarity 0.84)
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.
