Research map / Large language models / Language, safety and interpretability
A Morphology-Aware Network for Morphological Disambiguation
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 |
|---|---|---|---|
| Pre-train root embeddings instead of randomly initializing them (ablation) | Proposed morphology-aware network · Turkish | Morphological disambiguation accuracy: 84.12 -> 85.18 | Helped |
Closest papers by meaning
- Morphological Segmentation with Window LSTM Neural Networks (AAAI 2016 · similarity 0.87)
- A Latent Morphology Model for Open-Vocabulary Neural Machine Translation (ICLR 2020 · similarity 0.85)
- Linear Decoding of Morphology Relations in Language Models (Student Abstract) (AAAI 2025 · similarity 0.82)
- Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models (NeurIPS 2024 · similarity 0.82)
- Training Neural Networks as Recognizers of Formal Languages (ICLR 2025 · similarity 0.81)
- SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations (NeurIPS 2024 · 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.