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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add both attention regularizers R1 and R2 (ablation) | QAR-net · QR test set (Amazon) | F-measure: 0.4158 -> 0.5705 | Improved |
| add R1 (attention-similarity penalty) to R2-only (ablation) | QAR-net · QR test set (Amazon) | F-measure: 0.4610 -> 0.5705 | Improved |
| add R2 (Q-R representation distance) to R1-only (ablation) | QAR-net · QR test set (Amazon) | F-measure: 0.5097 -> 0.5705 | Improved |
| add QA-task pre-training (multi-task) before QR fine-tuning (ablation) | QAR-net · QR test set (Amazon) | F-measure: 0.4702 -> 0.5705 | Improved |
| naive hard-sharing MTL with QA data vs QR-only training | QA-net · QR test set (Amazon) | F-measure: 0.4647 -> 0.4471 | Hurt |
| use QAR-net architecture instead of QA-net with QR-only | QR training · QR test set (Amazon) | F-measure: 0.4647 -> 0.4702 | Improved |
| increase QA pre-training epochs beyond ~20 (ablation) | QAR-net · QR test set (Amazon) | validation F1 | Hurt |
Closest papers by meaning
- Dual Attention Network for Product Compatibility and Function Satisfiability Analysis (AAAI 2018 · similarity 0.85)
- A Question-Focused Multi-Factor Attention Network for Question Answering (AAAI 2018 · similarity 0.84)
- Hybrid Attentive Answer Selection in CQA With Deep Users Modelling (AAAI 2018 · similarity 0.84)
- Generative Question Answering: Learning to Answer the Whole Question (ICLR 2019 · similarity 0.83)
- Question-Driven Purchasing Propensity Analysis for Recommendation (AAAI 2020 · similarity 0.83)
- Attentive Interactive Neural Networks for Answer Selection in Community Question Answering (AAAI 2017 · similarity 0.83)
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.
