Research map / Label-efficient and robust learning / Recognition and long-tail
Latent Opinions Transfer Network for Target-Oriented Opinion Words Extraction
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Transfer latent opinion knowledge from sentiment classification data | PE-BiLSTM · 14res | F1: 78.26 -> 82.21 | Helped |
| Transfer latent opinion knowledge from sentiment classification data | PE-BiLSTM · 14lap | F1: 67.83 -> 72.02 | Helped |
| Transfer latent opinion knowledge from sentiment classification data | PE-BiLSTM · 15res | F1: 67.96 -> 73.29 | Helped |
| Transfer latent opinion knowledge from sentiment classification data | PE-BiLSTM · 16res | F1: 78.43 -> 83.62 | Helped |
| Add the pretrained sentiment-classification encoder (ablation) | PE-BiLSTM · 14res | F1: 78.26 -> 81.97 | Helped |
| Add the pretrained sentiment-classification encoder (ablation) | PE-BiLSTM · 14lap | F1: 67.83 -> 72.13 | Helped |
| Add the pretrained sentiment-classification encoder (ablation) | PE-BiLSTM · 15res | F1: 67.96 -> 72.26 | Helped |
| Add the pretrained sentiment-classification encoder (ablation) | PE-BiLSTM · 16res | F1: 78.43 -> 82.79 | Helped |
| Add auxiliary learning from latent opinion-word pseudo-labels (ablation) | PE-BiLSTM · 14res | F1: 78.26 -> 80.49 | Helped |
| Add auxiliary learning from latent opinion-word pseudo-labels (ablation) | PE-BiLSTM · 14lap | F1: 67.83 -> 70.71 | Helped |
| Add auxiliary learning from latent opinion-word pseudo-labels (ablation) | PE-BiLSTM · 15res | F1: 67.96 -> 72.29 | Helped |
| Add auxiliary learning from latent opinion-word pseudo-labels (ablation) | PE-BiLSTM · 16res | F1: 78.43 -> 82.93 | Helped |
Closest papers by meaning
- A Unified Model for Opinion Target Extraction and Target Sentiment Prediction (AAAI 2019 · similarity 0.86)
- Transferable Interactive Memory Network for Domain Adaptation in Fine-Grained Opinion Extraction (AAAI 2019 · similarity 0.85)
- Recurrent Neural Networks with Auxiliary Labels for Cross-Domain Opinion Target Extraction (AAAI 2017 · similarity 0.85)
- Gated Neural Networks for Targeted Sentiment Analysis (AAAI 2016 · similarity 0.84)
- Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentations (AAAI 2024 · similarity 0.81)
- Intelligent Calibration for Bias Reduction in Sentiment Corpora Annotation Process (AAAI 2024 · similarity 0.81)
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.