AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Generating Character Descriptions for Automatic Summarization of Fiction

Weiwei Zhang, Jackie Chi Kit Cheung, Joel Oren

AAAI 2019 · Large language models › Language, safety and interpretability · approach: Controlled text generation

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
use abstractive classifier (attr + relevant + full contexts) instead of SVM baselinecharacter attribute prediction · Author-annotated character attributesRecall@4: 0.0505 -> 0.1266Improved
use abstractive classifier instead of extractive rankingcharacter attribute prediction · Author-annotated character attributesRecall@4: 0.0631 -> 0.1266Improved
add full-context features to extractive ranker (ablation)extractive GBDT · Author-annotated character attributesRecall@4: 0.0631 -> 0.0631No clear effect
add relevant-sentence context to abstractive classifier with attribute only vs combination (ablation)abstractive classifier · Author-annotated character attributesRecall@4: 0.1193 -> 0.1266Improved
add relevant sentence to full contexts (ablation)abstractive classifier · Author-annotated character attributesRecall@4: 0.1104 -> 0.1266Improved
replace full contexts with relevant sentence (ablation)abstractive classifier · Author-annotated character attributesRecall@4: 0.1104 -> 0.1193Improved
abstractive (candidates from corpus list) instead of extractive (story text only)attribute candidate source · Author-annotated character attributesRecall@4: 0.0631 -> 0.1193Improved
use top-1 most similar sentence instead of top-k (ablation)abstractive classifier · Author-annotated character attributesvalidation performanceImproved
classification target instead of similarity regression for abstractive modelabstractive classifier · Author-annotated character attributeslabel qualityImproved

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