AI Paper Atlas

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

Filling Conversation Ellipsis for Better Social Dialog Understanding

Xiyuan Zhang, Chengxi Li, Dian Yu, Samuel Davidson, Zhou Yu

AAAI 2020 · Large language models › Language, safety and interpretability · approach: Faithfulness of LLM explanations · 14 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
Combine predictions from original and automatically completed utterancesDialog act prediction with BERT · GunrockF1 (%): 79.65 -> 80.90Improved
Use automatically completed utterances only instead of original utterancesDialog act prediction with BERT · GunrockF1 (%): 79.65 -> 78.04Hurt
Add a copy mechanism to Seq2Seq (ablation)Utterance completion · GunrockBLEU (%): 42.36 -> 71.85Improved
Combine original and completed utterance SRL predictionsSemantic role labeling with stacked Bi-LSTMs · GunrockF1 (%): 88.39 -> 90.87Improved
Use completed utterances only instead of original utterancesSemantic role labeling with stacked Bi-LSTMs · GunrockF1 (%): 88.39 -> 87.50Hurt
Add expert knowledge to logit addition during selection (ablation)Dialog act prediction with BERT · GunrockF1 (%): 80.85 -> 80.90Improved
Use maximum rather than addition to combine logits (ablation)Dialog act prediction with BERT · GunrockF1 (%): 79.85 vs 80.85Hurt
Combine hidden states by addition rather than using logit addition (ablation)Dialog act prediction with BERT · GunrockF1 (%): 80.08 vs 80.85Hurt
Combine hidden states by concatenation rather than using logit addition (ablation)Dialog act prediction with BERT · GunrockF1 (%): 79.65 vs 80.85Hurt
Combine hidden states by maximum rather than using logit addition (ablation)Dialog act prediction with BERT · GunrockF1 (%): 79.63 vs 80.85Hurt
Use probability-based rather than rule-based expert knowledge for SRL selection (ablation)Hybrid-EL-CMP · GunrockF1 (%): 90.62 -> 90.87Improved
Train two models on original utterances instead of using a single original-utterance model (ablation)Dialog act prediction with BERT · GunrockF1 (%): 79.65 -> 79.70Improved

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