Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.18326 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910028098699264 |
|---|---|
| author | Wu, Tao Kapelner, Adam |
| author_facet | Wu, Tao Kapelner, Adam |
| contents | We describe a modern deep learning system that automatically identifies informative contextual examples (\qu{contexts}) for first language vocabulary instruction for high school student. Our paper compares three modeling approaches: (i) an unsupervised similarity-based strategy using MPNet's uniformly contextualized embeddings, (ii) a supervised framework built on instruction-aware, fine-tuned Qwen3 embeddings with a nonlinear regression head and (iii) model (ii) plus handcrafted context features. We introduce a novel metric called the Retention Competency Curve to visualize trade-offs between the discarded proportion of good contexts and the \qu{good-to-bad} contexts ratio providing a compact, unified lens on model performance. Model (iii) delivers the most dramatic gains with performance of a good-to-bad ratio of 440 all while only throwing out 70\% of the good contexts. In summary, we demonstrate that a modern embedding model on neural network architecture, when guided by human supervision, results in a low-cost large supply of near-perfect contexts for teaching vocabulary for a variety of target words. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_18326 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Predicting Contextual Informativeness for Vocabulary Learning using Deep Learning Wu, Tao Kapelner, Adam Computation and Language We describe a modern deep learning system that automatically identifies informative contextual examples (\qu{contexts}) for first language vocabulary instruction for high school student. Our paper compares three modeling approaches: (i) an unsupervised similarity-based strategy using MPNet's uniformly contextualized embeddings, (ii) a supervised framework built on instruction-aware, fine-tuned Qwen3 embeddings with a nonlinear regression head and (iii) model (ii) plus handcrafted context features. We introduce a novel metric called the Retention Competency Curve to visualize trade-offs between the discarded proportion of good contexts and the \qu{good-to-bad} contexts ratio providing a compact, unified lens on model performance. Model (iii) delivers the most dramatic gains with performance of a good-to-bad ratio of 440 all while only throwing out 70\% of the good contexts. In summary, we demonstrate that a modern embedding model on neural network architecture, when guided by human supervision, results in a low-cost large supply of near-perfect contexts for teaching vocabulary for a variety of target words. |
| title | Predicting Contextual Informativeness for Vocabulary Learning using Deep Learning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.18326 |