AI Paper Atlas

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

Answer Identification from Product Reviews for User Questions by Multi-Task Attentive Networks

Long Chen, Ziyu Guan, Wei Zhao, Wanqing Zhao, Xiaopeng Wang, Zhou Zhao, Huan Sun

AAAI 2019 · Vision-language and multimodal › Visual question answering · approach: Open-domain multimodal QA · 22 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 both attention regularizers R1 and R2 (ablation)QAR-net · QR test set (Amazon)F-measure: 0.4158 -> 0.5705Improved
add R1 (attention-similarity penalty) to R2-only (ablation)QAR-net · QR test set (Amazon)F-measure: 0.4610 -> 0.5705Improved
add R2 (Q-R representation distance) to R1-only (ablation)QAR-net · QR test set (Amazon)F-measure: 0.5097 -> 0.5705Improved
add QA-task pre-training (multi-task) before QR fine-tuning (ablation)QAR-net · QR test set (Amazon)F-measure: 0.4702 -> 0.5705Improved
naive hard-sharing MTL with QA data vs QR-only trainingQA-net · QR test set (Amazon)F-measure: 0.4647 -> 0.4471Hurt
use QAR-net architecture instead of QA-net with QR-onlyQR training · QR test set (Amazon)F-measure: 0.4647 -> 0.4702Improved
increase QA pre-training epochs beyond ~20 (ablation)QAR-net · QR test set (Amazon)validation F1Hurt

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