AI Paper Atlas

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

Deep Cascade Multi-Task Learning for Slot Filling in Online Shopping Assistant

Yu Gong, Xusheng Luo, Yu Zhu, Wenwu Ou, Zhao Li, Muhua Zhu, Kenny Q. Zhu, Lu Duan, Xi Chen

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
Use DCMTL with cascade and residual connections instead of Hierarchy Multi-taskECSA slot filling · ECSAF1: 0.4455 -> 0.5105Improved
Add residual connections (ablation)DCMTL · ECSAF1: 0.4840 -> 0.5105Improved
Add cascade connections (ablation)DCMTL · ECSAF1: 0.4633 -> 0.5105Improved
Use hierarchical multi-task learning rather than vanilla shared-encoder multi-task learning (ablation)ECSA slot filling · ECSAF1: 0.3965 -> 0.4455Improved
Provide the gold segment type as an input featureBasic BiLSTM-CRF · ECSAF1: 0.4302 -> 0.7950Improved
Provide the gold named entity type as an input featureBasic BiLSTM-CRF · ECSAF1: 0.4302 -> 0.8985Improved
Deploy DCMTL instead of online max-matchingOnline shopping assistant · ECSA online queriesaccuracy: 26.37% -> 60.53%; 130% improvementImproved
Use DCMTL instead of Neural Sequence ChunkingATIS slot filling · ATISF1: 0.9586 -> 0.9583; F1-0.03%No clear effect
Use DCMTL instead of Sequential CNNATIS slot filling · ATISF1: 0.9561 -> 0.9583; F1+0.22%Improved
Use cascade type 3, with segment tagging, named entity tagging, and slot filling in sequence, rather than a skipped connection (ablation)DCMTL · ECSAF1Improved

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