Research map / Architectures and efficiency / Attention and transformers
Enhancing Pointer Network for Sentence Ordering with Pairwise Ordering Predictions
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 FUTURE module (Pd) to pointer decoder (ablation) | Ours · ROCStory | PMR: 40.92 -> 46.00 | Helped |
| add FUTURE module (Pd) to pointer decoder (ablation) | Ours · SIND | PMR: 15.73 -> 17.37 | Helped |
| add HISTORY module Pl1 (distance 1) (ablation) | Ours · ROCStory | PMR: 44.66 -> 46.00 | Helped |
| add HISTORY module Pl2 (distance 2) (ablation) | Ours · SIND | PMR: 17.10 -> 17.37 | Helped |
| add HISTORY module Pl2 (distance 2) (ablation) | Ours · arXiv | Kendall tau: 76.46 -> 76.65 | Helped |
| feed pairwise predictions into decoder instead of only multi-task loss | Ours · ROCStory | PMR: 41.29 -> 46.00 | Helped |
| add pairwise-module decoder enhancement to ATTOrderNet baseline | Ours · ROCStory | PMR: 40.01 -> 46.00 | Helped |
| replace masked self-attention decoder with pairwise-enhanced decoder | Ours · SIND | PMR: 15.43 -> 17.37 | Helped |
| add pairwise ordering multi-task losses only (MTL) | Baseline · SIND | Kendall tau: 51.67 -> 52.28 | No clear effect |
| use pairwise-enhanced ordering for summary reordering | Ours · DUC 2004 | coherence: 45.92 -> 48.67 | Helped |
Closest papers by meaning
- Neural Sentence Ordering Based on Constraint Graphs (AAAI 2021 · similarity 0.88)
- Short-Context Dominance: How Much Local Context Natural Language Actually Needs? (NeurIPS 2026 · similarity 0.85)
- Order-Independence Without Fine Tuning (NeurIPS 2024 · similarity 0.84)
- Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding (ICML 2025 · similarity 0.84)
- Eliminating Position Bias of Language Models: A Mechanistic Approach (ICLR 2025 · similarity 0.84)
- Implicit Word Reordering with Knowledge Distillation for Cross-Lingual Dependency Parsing (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.