AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Response Generation by Context-Aware Prototype Editing

Yu Wu, Furu Wei, Shaohan Huang, Yunli Wang, Zhoujun Li, Ming Zhou

AAAI 2019 · Large language models › Retrieval and knowledge · approach: Retrieval-augmented reasoning

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 a prototype response and context-aware editing instead of generating from scratchResponse generation · Douban testNot appear: 0.745 -> 0.860Improved
Use prototype-then-edit rather than a traditional generative modelResponse generation · Douban testDistinct-2: 0.178 -> 0.280Improved
Edit retrieved candidates and rerank themRetrieval response generation · Douban testAverage: 0.380 -> 0.386Improved
Edit one top-ranked retrieval response before rerankingRetrieval response generation · Douban testAverage: 0.380 -> 0.367Hurt
Add context insertion words to the edit vector (ablation)Context-aware neural editor · Douban testAverage: 34.2 -> 38.6Improved
Add context deletion words to the edit vector (ablation)Context-aware neural editor · Douban testAverage: 34.0 -> 38.6Improved
Add context-aware insertion and deletion information rather than standard Seq2Seq editing (ablation)Context-aware neural editor · Douban testAverage: 32.8 -> 38.6Improved
Add context insertion words to the edit vector (ablation)Context-aware neural editor · Douban testOriginality: 85.1 -> 86.0No clear effect
Add context deletion words to the edit vector (ablation)Context-aware neural editor · Douban testOriginality: 86.3 -> 86.0No clear effect
Add context-aware insertion and deletion information (ablation)Context-aware neural editor · Douban testDis-2: 0.282 -> 0.280No clear effect

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