AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Neural Simile Recognition with Cyclic Multitask Learning and Local Attention

Jiali Zeng, Linfeng Song, Jinsong Su, Jun Xie, Wei Song, Jiebo Luo

AAAI 2020 · Architectures and efficiency › Attention and transformers · approach: Sparse and structured attention · 23 citations (OpenAlex)

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 changedWhereMeasuredEffect
replace global attention with local attention around the comparator (ablation)simile sentence classifier · Chinese simile classificationF1-score: 82.84 -> 83.79Improved
connect subtasks cyclically instead of using conventional shared-task MTL (ablation)simile classification · Chinese simile sentence classificationF1-score: 86.53 -> 87.04Improved
connect subtasks cyclically instead of using conventional shared-task MTL (ablation)simile component extraction · Chinese simile component extractionF1-score: 62.68 -> 68.05Improved
increase cyclic execution from K=0 to K=1 (ablation)MTL-Cyc · Chinese simile classification, validationF1-score: 86.09 -> 86.62Improved
increase cyclic execution from K=0 to K=1 (ablation)MTL-Cyc · Chinese simile component extraction, validationF1-score: 63.15 -> 73.33Improved
increase cyclic execution from K=1 to K=2 (ablation)MTL-Cyc · Chinese simile classification and component extraction, validationF1-score: 86.62 -> 86.65; 73.33 -> 73.40No clear effect
increase cyclic execution beyond K=2 (ablation)MTL-Cyc · Chinese simile classification and component extraction, validationF1-score: 86.65 -> 85.89; 73.40 -> 72.83Hurt
add sentence reconstruction as an auxiliary task (ablation)MTL simile component extractor · Chinese simile component extractionF1-score: 59.89 -> 63.29Improved
order the pipeline as classification → extraction rather than extraction → classification (ablation)MTL-Pip · Chinese simile sentence classificationF1-score: 85.20 -> 85.51Improved
order the pipeline as classification → extraction rather than extraction → classification (ablation)MTL-Pip · Chinese simile component extractionF1-score: 61.84 -> 66.45Improved
use cyclic connections rather than a classification → extraction → reconstruction pipeline (ablation)simile classifier · Chinese simile sentence classificationF1-score: 86.81 -> 87.04Improved
use cyclic connections rather than a classification → extraction → reconstruction pipeline (ablation)simile component extractor · Chinese simile component extractionF1-score: 67.63 -> 68.05Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy