atlas

Research map / Large language models / Retrieval and knowledge

Exploring Auxiliary Reasoning Tasks for Task-oriented Dialog Systems with Meta Cooperative Learning

AAAI 2021 · Large language models › Retrieval and knowledge · approach: Explanatory and multiple-choice QA benchmarks · 10 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 meta-cooperatively learned KB and dialogue reasoning auxiliariesTask-oriented dialogue generation · CamRestBLEU: 20.1 vs 18.5Helped
Add meta-cooperatively learned KB and dialogue reasoning auxiliariesTask-oriented dialogue generation · CamRestEntity F1: 59.2 vs 58.6Helped
Add meta-cooperatively learned KB and dialogue reasoning auxiliariesTask-oriented dialogue generation · In-Car AssistantBLEU: 17.2 vs 14.8Helped
Add meta-cooperatively learned KB and dialogue reasoning auxiliariesTask-oriented dialogue generation · In-Car AssistantEntity F1: 60.9 vs 60.0Helped
Add meta-cooperatively learned KB and dialogue reasoning auxiliariesTask-oriented dialogue generation · Multi-WOZ 2.1BLEU: 13.6 vs 9.2Helped
Add meta-cooperatively learned KB and dialogue reasoning auxiliariesTask-oriented dialogue generation · Multi-WOZ 2.1Entity F1: 32.6 vs 32.4Helped
Add meta learning to adapt the auxiliary reasoning networks (ablation)MCL · CamRestBLEU: 20.0 -> 20.1No clear effect
Add meta learning to adapt the auxiliary reasoning networks (ablation)MCL · CamRestEntity F1: 55.2 -> 58.2Helped
Add meta learning to adapt the auxiliary reasoning networks (ablation)MCL · In-Car AssistantBLEU: 15.2 -> 17.2Helped
Add meta learning to adapt the auxiliary reasoning networks (ablation)MCL · Multi-WOZ 2.1BLEU: 10.3 -> 13.6Helped
Add the auxiliary KB reasoning task (ablation)MCL · CamRestBLEU: 17.6 -> 20.1Helped
Add the auxiliary dialogue reasoning task (ablation)MCL · CamRestBLEU: 15.7 -> 20.1Helped

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