Research map / Architectures and efficiency / Attention and transformers
Multi-Channel Reverse Dictionary Model
Lei Zhang, Fanchao Qi, Zhiyuan Liu, Yasheng Wang, Qun Liu, Maosong Sun
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 |
|---|---|---|---|
| Combine word prediction with multiple characteristic predictors | BiLSTM reverse dictionary · English unseen Definition | accuracy@1: .07 -> .09 | Improved |
| Combine word prediction with multiple characteristic predictors | BiLSTM reverse dictionary · Chinese Question | accuracy@1: .30 -> .50 | Improved |
| Use Multi-channel instead of OneLook | English reverse dictionary · English Description | accuracy@1: .33 -> .32 | Hurt |
| Add morpheme predictor (ablation) | BiLSTM reverse dictionary · English unseen Definition | accuracy@1: .07 -> .08 | Improved |
| Add word category predictor (ablation) | BiLSTM reverse dictionary · English unseen Definition | accuracy@1: .07 -> .08 | Improved |
| Add sememe predictor (ablation) | BiLSTM reverse dictionary · English unseen Definition | accuracy@1: .07 -> .08 | Improved |
| Add POS predictor (ablation) | BiLSTM reverse dictionary · Chinese Question | accuracy@1: .30 -> .25 | Hurt |
| Add morpheme predictor (ablation) | BiLSTM reverse dictionary · Chinese Question | accuracy@1: .30 -> .42 | Improved |
| Add word category predictor (ablation) | BiLSTM reverse dictionary · Chinese Question | accuracy@1: .30 -> .33 | Improved |
| Add sememe predictor (ablation) | BiLSTM reverse dictionary · Chinese Question | accuracy@1: .30 -> .34 | Improved |
| Filter candidates using the target word's initial letter | Multi-channel · English Description | accuracy@1: .32 -> .62 | Improved |
| Filter candidates using the target word's length | Multi-channel · English Description | accuracy@1: .32 -> .55 | Improved |
Closest papers by meaning
- Language Model Decoding as Direct Metrics Optimization (ICLR 2024 · similarity 0.81)
- Decoding-Time Language Model Alignment with Multiple Objectives (NeurIPS 2024 · similarity 0.81)
- Rep2Text: Decoding Full Text from a Single LLM Token Representation (NeurIPS 2026 · similarity 0.81)
- Retrieval-based Disentangled Representation Learning with Natural Language Supervision (ICLR 2024 · similarity 0.80)
- Towards a Transformer-Based Reverse Dictionary Model for Quality Estimation of Definitions (Student Abstract) (AAAI 2024 · similarity 0.80)
- Time-Reversal Provides Unsupervised Feedback to LLMs (NeurIPS 2024 · similarity 0.80)
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.
