Research map / Label-efficient and robust learning / Recognition and long-tail
Sentence Ordering and Coherence Modeling using Recurrent Neural Networks
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 |
|---|---|---|---|
| Use the set-to-sequence ordering model rather than the strongest listed baseline | Sentence ordering model · NIPS, AAN, and NSF Abstracts | accuracy: 48.22 -> 51.55; 52.06 -> 58.06; 25.79 -> 28.33 | Helped |
| Pre-train on the sentence ordering task before summarization fine-tuning | Extractive summarization model · CNN summarization, both reported summary lengths | ROUGE-1: 18.29 -> 18.77; 35.82 -> 36.47 | Helped |
| Add a BoW representation to the ordering-model sentence embeddings (ablation) | Ordering model · SICK | r: 0.807 -> 0.842 | Helped |
| Add a BoW representation to the ordering-model sentence embeddings (ablation) | Ordering model · MSRP | accuracy: 72.3 -> 74.0 | Helped |
| Use the bilinear scoring function (ablation) | Sentence ordering model representations · Sentence representation evaluation | representation quality | Helped |
| Add contrastive sentences to the decoder memory (ablation) | Sentence ordering model representations · Sentence representation evaluation | representation quality | Helped |
| Add global context through the set encoder to the local window approach | Sentence ordering model · Abstract sentence ordering | accuracy: 41.76 -> 51.55; 50.87 -> 58.06; 18.67 -> 28.33 | Helped |
Closest papers by meaning
- Hierarchical Attention Networks for Sentence Ordering (AAAI 2019 · similarity 0.90)
- Deep Attentive Ranking Networks for Learning to Order Sentences (AAAI 2020 · similarity 0.88)
- Enhancing Pointer Network for Sentence Ordering with Pairwise Ordering Predictions (AAAI 2020 · similarity 0.87)
- Neural Sentence Ordering Based on Constraint Graphs (AAAI 2021 · similarity 0.87)
- Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks (ICLR 2019 · similarity 0.87)
- Neural Models for Sequence Chunking (AAAI 2017 · similarity 0.85)
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.