AI Paper Atlas

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

FANDA: A Novel Approach to Perform Follow-Up Query Analysis

Qian Liu, Bei Chen, Jian-Guang Lou, Ge Jin, Dongmei Zhang

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 FAnDa instead of Copy+AnonFollow-up query analysis · FollowUp testSymbol Accuracy: 27.00 ± 4.32 -> 47.80 ± 1.14Improved
Use FAnDa instead of Copy+AnonFollow-up query analysis · FollowUp testBLEU: 49.43 ± 1.11 -> 59.02 ± 0.54Improved
Use FAnDa instead of Copy+AnonFollow-up query analysis · FollowUp testExecution Accuracy: 40.77 -> 60.19Improved
Add anonymization to CopyNetCopyNet · FollowUp testSymbol Accuracy: 19.30 ± 0.93 -> 27.00 ± 4.32Improved
Add intent classification instead of assigning Refine to every follow-up (ablation)FAnDa · FollowUp testSymbol Accuracy: 35.30 ± 0.44 -> 47.80 ± 1.14Improved
Add intent classification instead of assigning Refine to every follow-up (ablation)FAnDa · FollowUp testBLEU: 55.01 ± 0.86 -> 59.02 ± 0.54Improved
Use the ranking model instead of randomly selecting a segment sequence (ablation)FAnDa · FollowUp testSymbol Accuracy: 24.30 ± 6.70 -> 47.80 ± 1.14Improved
Use the ranking model instead of randomly selecting a segment sequence (ablation)FAnDa · FollowUp testBLEU: 52.92 ± 2.24 -> 59.02 ± 0.54Improved
Add supervised pretraining on manually annotated tags from 100 training triples (ablation)FAnDa · FollowUp testSymbol Accuracy: 47.80 ± 1.14 -> 48.20 ± 1.02Improved
Add supervised pretraining on manually annotated tags from 100 training triples (ablation)FAnDa · FollowUp testBLEU: 59.02 ± 0.54 -> 59.87 ± 0.43Improved

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