AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Semi-Distantly Supervised Neural Model for Generating Compact Answers to Open-Domain Why Questions

Ryo Ishida, Kentaro Torisawa, Jong-Hoon Oh, Ryu Iida, Canasai Kruengkrai, Julien Kloetzer

AAAI 2018 · Vision-language and multimodal › Visual question answering · approach: Open-domain multimodal QA · 8 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
add question word marking to pointer-generator network (ablation)PG · Why-QA compact answers test setROUGE-1: 36.5 -> 38.2Improved
add query attention to PG (ablation)PG · Why-QA compact answers test setROUGE-1: 36.5 -> 36.1Hurt
add 250K auto-generated training data to manual data (ablation)Proposed · Why-QA compact answers test setROUGE-1: 38.2 -> 44.9Improved
add 250K auto-generated training data to manual data (ablation)Proposed · Why-QA compact answers test setROUGE-2: 21.6 -> 31.0Improved
increase auto-generated data from 250K to 500K (ablation)Proposed+N · Why-QA compact answers test setROUGE-1: 44.9 -> 44.1No clear effect
increase auto-generated data from 250K to 1M (ablation)Proposed+N · Why-QA compact answers test setROUGE-1: 44.9 -> 44.4No clear effect
train on 250K auto-generated data only, without manual data (ablation)Proposed+250K · Why-QA compact answers test setROUGE-1: 44.9 -> 28.6Hurt
compare PG against DrQA span extraction (ablation)PG · Why-QA compact answers test setROUGE-1: 36.5 -> 24.7Hurt
pointer-generator vs CRF causal-relation extraction (ablation)Proposed · Why-QA compact answers test setROUGE-1: 32.7 -> 38.2Improved
use Proposed+750K instead of Proposed (ablation)Proposed · Fluency (human)Good label ratio (%): 61.2% -> 65.7%Improved
add question word marking (ablation)PG · Fluency (human)Good label ratio (%): 52.7% -> 61.2%Improved
use Proposed+750K instead of Proposed (ablation)Proposed · Informativeness (human, question only)Good label ratio (%): 17.1% -> 24.1%Improved

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