AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

A Multi-Agent Communication Framework for Question-Worthy Phrase Extraction and Question Generation

Siyuan Wang, Zhongyu Wei, Zhihao Fan, Yang Liu, Xuanjing Huang

AAAI 2019 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Theory-of-mind social reasoning

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
pass question information from the generation agent to the extraction agent (E_MP vs E_Local) (ablation)phrase extractor · SQuAD sentence-level test phrase extractionexact match: 24.27% -> 35.77%Improved
pass question information from the generation agent (E_MP vs E_Local) (ablation)phrase extractor · SQuAD sentence-level test phrase extractionF1: 38.63 -> 46.71Improved
pointer-network extractor instead of Stanford NERphrase extractor · SQuAD sentence-level test phrase extractionF1: 17.33 -> 38.63Improved
message passing reduces overlapping phrases (ablation)phrase extractor · SQuAD sentence-level test phrase extractionsentences with overlapped phrases: 32.37% -> 22.05%Improved
message passing discards mis-extracted phrases (ablation)phrase extractor · SQuAD sentence-level test phrase extractionavg. number of extracted phrases: 1.43 -> 1.38Mixed
use extracted phrases from E_MP trained jointly instead of E_Local phrases (ablation)question generator · SQuAD sentence-level test question generationBLEU-4: 9.76 -> 10.56Improved
use extracted phrases from E_MP instead of E_Local phrases (ablation)question generator · SQuAD sentence-level test question generationBLEU-1: 44.36 -> 45.70Improved
use extracted phrases from E_MP instead of E_Local phrases (ablation)question generator · SQuAD sentence-level test question generationROUGE-L: 37.00 -> 38.09Improved
feed NER-extracted phrases as extra input vs no phrase information (ablation)question generator · SQuAD sentence-level test question generationBLEU-4: 9.05 -> 9.22No clear effect
feed E_MP phrases instead of no phrase information (ablation)question generator · SQuAD sentence-level test question generationBLEU-4: 9.05 -> 10.56Improved
feed E_MP phrases instead of no phrase information (ablation)question generator · SQuAD sentence-level test question generationMETEOR: 14.63 -> 15.76Improved
use ground-truth answers instead of extracted phrases (upper bound) (ablation)question generator · SQuAD sentence-level test question generationBLEU-4: 10.56 -> 11.81Improved

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