Research map / Label-efficient and robust learning / Recognition and long-tail
GIRNet: Interleaved Multi-Task Recurrent State Sequence Models
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 |
|---|---|---|---|
| Use GIRNet's position-sensitive gated interleaving of auxiliary states | Code-switched sentiment classification · Code-switched sentiment classification | Accuracy | Helped |
| Use GIRNet's position-sensitive gated interleaving of auxiliary states | Code-switched POS tagging · Code-switched POS tagging | Macro F1 | Helped |
| Use GIRNet with whole-passage sentiment as an auxiliary task | Laptop target-dependent sentiment · Laptop | Macro F1 | Helped |
| Use GIRNet with whole-passage sentiment as an auxiliary task | Restaurant target-dependent sentiment · Restaurant | Macro F1 | Helped |
| Use two LSTM layers instead of one in GIRNet (ablation) | GIRNet · Code-switched sentiment classification | Accuracy | Hurt |
| Use two LSTM layers instead of one in GIRNet (ablation) | GIRNet · Code-switched POS tagging | Accuracy | Hurt |
| Use two LSTM layers instead of one in GIRNet (ablation) | GIRNet · Laptop | Accuracy | Helped |
| Use two LSTM layers instead of one in GIRNet (ablation) | GIRNet · Restaurant | Accuracy | Hurt |
Closest papers by meaning
- Focused Hierarchical RNNs for Conditional Sequence Processing (ICML 2018 · similarity 0.86)
- Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks (ICLR 2017 · similarity 0.86)
- Agreement on Target-Bidirectional LSTMs for Sequence-to-Sequence Learning (AAAI 2016 · similarity 0.86)
- TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency (ICLR 2017 · similarity 0.85)
- Bridging Towers of Multi-task Learning with a Gating Mechanism for Aspect-based Sentiment Analysis and Sequential Metaphor Identification (AAAI 2021 · similarity 0.85)
- Empower Sequence Labeling with Task-Aware Neural Language Model (AAAI 2018 · similarity 0.85)
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.