Research map / Architectures and efficiency / RNNs and normalization
A Neural Network Approach to Verb Phrase Ellipsis Resolution
Wei-Nan Zhang, Yue Zhang, Yuanxing Liu, Donglin Di, Ting Liu
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 hand-crafted features F of Kenyon-Dean et al. (ablation) | Transformer · VPE detection 5-fold CV | F1: 0.88 -> 0.96 | Improved |
| add features F (ablation) | MLP · VPE detection 5-fold CV | F1: 0.87 -> 0.95 | Improved |
| add features F (ablation) | SVM · VPE detection 5-fold CV | F1: 0.87 -> 0.90 | Improved |
| replace SVM/ML with Transformer, same features | SVM · VPE detection 5-fold CV | F1: 0.87 -> 0.88 | Improved |
| replace SVM+F with Transformer+F | SVM+F · VPE detection 5-fold CV | F1: 0.90 -> 0.96 | Improved |
| add features F to AttGRU encoder (ablation) | MLP · VPE resolution 5-fold CV | accuracy: 0.53 -> 0.87 | Improved |
| add features F to GRU encoder (ablation) | MLP · VPE resolution 5-fold CV | accuracy: 0.51 -> 0.78 | Improved |
| add features F to Sum encoder (ablation) | Transformer · VPE resolution 5-fold CV | accuracy: 0.83 -> 0.88 | Improved |
| use attention-based GRU instead of sum pooling (ablation) | MLP+F · VPE resolution 5-fold CV | accuracy: 0.76 -> 0.87 | Improved |
| use attention-based GRU instead of sum pooling (ablation) | Transformer+F · VPE resolution 5-fold CV | accuracy: 0.88 -> 0.94 | Improved |
| use Transformer instead of MLP without features, GRU encoder (ablation) | GRU encoder · VPE resolution 5-fold CV | accuracy: 0.51 -> 0.85 | Improved |
| neural models vs MIRA baseline in resolution | AttGRU+F · VPE resolution 5-fold CV | accuracy: 0.65 -> 0.94 | Improved |
Closest papers by meaning
- Verbs in Action: Improving Verb Understanding in Video-Language Models (ICCV 2023 · similarity 0.84)
- WinoGrande: An Adversarial Winograd Schema Challenge at Scale (AAAI 2020 · similarity 0.83)
- Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words (ICLR 2025 · similarity 0.81)
- Verb Mirage: Unveiling and Assessing Verb Concept Hallucinations in Multimodal Large Language Models (AAAI 2026 · similarity 0.81)
- Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models (NeurIPS 2025 · similarity 0.81)
- SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability (ICML 2025 · similarity 0.81)
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.
