AI Paper Atlas

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

An Affect-Rich Neural Conversational Model with Biased Attention and Weighted Cross-Entropy Loss

Peixiang Zhong, Di Wang, Chunyan Miao

AAAI 2019 · Large language models › Language, safety and interpretability · approach: Faithfulness of LLM explanations

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
Add local-importance affective attention and affective objectiveSeq2Seq with attention · DailyDialog out-domain testperplexity: 124.3 -> 113.7Improved
Add local-importance affective attention and affective objectiveSeq2Seq with attention · Preference testcontent preference: 66 (+3.1%) -> 80 (+25.0%)Improved
Add local-importance affective attention and affective objectiveSeq2Seq with attention · Preference testemotion preference: 32 (+23.1%) -> 49 (+88.5%)Improved
Add local-importance affective attention (ablation)Seq2Seq with attention · MCTemotion quality score: 0.712 -> 0.856 (+20.2%)Improved
Add affective objective (ablation)Seq2Seq with attention · MCTemotion quality score: 0.712 -> 0.828 (+16.3%)Improved
Combine local-importance affective attention with affective objective (ablation)Seq2Seq with attention · MCTemotion quality score: 0.712 -> 0.908 (+27.5%)Improved
Replace uniform term importance with global term importance (ablation)affective attention · MCTemotion quality score: 0.832 -> 0.862 (+16.9% -> +21.1%)Improved
Replace global term importance with local term importance (ablation)affective attention · MCTemotion quality score: 0.862 -> 0.856No clear effect
Increase affective loss coefficient δ (ablation)S2S-AO · MCT test responsesdistinct affect-rich words (VAD norm threshold 3): 36 -> 50 -> 69Improved
Increase affective attention coefficient γ beyond its small-value range (ablation)affective attention · test responsesdistinct affect-rich wordsHurt
Set γ in the range [20, ∞] (ablation)affective attention · test responsesresponse lengthHurt
Increase affect embedding strength λ from 0 to 0.3 (ablation)AR-S2S · test responsesdistinct affect-rich wordsImproved

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