Research map / Label-efficient and robust learning / Semi-supervised learning
An Adaptive Layer to Leverage Both Domain and Task Specific Information from Scarce Data
Gaël Guibon, Matthieu Labeau, Luce Lefeuvre, Chloé Clavel
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 |
|---|---|---|---|
| Use TAFT instead of TAPT | DistilCamemBERT · Customer Satisfaction | weighted F1: 46.34 -> 62.92 | Improved |
| Use TAFT instead of DAPT | DistilCamemBERT · Problematic Conversation | weighted F1: 85.51 -> 73.67 | Hurt |
| Use TAFT instead of standard fine-tuning | DistilCamemBERT · Problem Status | weighted F1: 44.37 -> 51.88 | Improved |
| Add multi-task fine-tuning for satisfaction and problem status (ablation) | TAFT on customer service conversations · Customer Satisfaction | weighted F1: 40.01 -> 62.92 | Improved |
| Add multi-task fine-tuning for satisfaction and problem status (ablation) | TAFT on customer service conversations · Problematic Conversation | weighted F1: 17.85 -> 73.67 | Improved |
| Add multi-task fine-tuning for satisfaction and problem status (ablation) | TAFT on customer service conversations · Problem Status | weighted F1: 17.48 -> 51.88 | Improved |
| Add an adaptive layer (ablation) | TAFT on customer service conversations · Customer Satisfaction | weighted F1: 57.47 -> 62.92 | Improved |
| Add an adaptive layer (ablation) | TAFT on customer service conversations · Problematic Conversation | weighted F1: 49.98 -> 73.67 | Improved |
| Add an adaptive layer (ablation) | TAFT on customer service conversations · Problem Status | weighted F1: 36.00 -> 51.88 | Improved |
Closest papers by meaning
- A Framework for Mining Speech-to-Text Transcripts of the Customer for Automated Problem Remediation (AAAI 2024 · similarity 0.85)
- icsPLMs: Exploring Pre-trained Language Models in Intelligent Customer Service (Student Abstract) (AAAI 2024 · similarity 0.84)
- Talk, Snap, Complain: Validation-Aware Multimodal Expert Framework for Fine-Grained Customer Grievances (AAAI 2026 · similarity 0.80)
- LEGEND: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets (AAAI 2025 · similarity 0.80)
- Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training (ICLR 2025 · similarity 0.79)
- Response Enhanced Semi-supervised Dialogue Query Generation (AAAI 2024 · similarity 0.79)
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.
