Summary of Semi-supervised Dialogue Abstractive Summarization Via High-quality Pseudolabel Selection, by Jianfeng He et al.
Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection
by Jianfeng He, Hang Su, Jason Cai, Igor Shalyminov, Hwanjun Song, Saab Mansour
First submitted to arxiv on: 6 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers tackle the problem of semi-supervised dialogue summarization (SSDS), aiming to reduce reliance on human-labeled data and improve summarization model performance. The existing approaches for semi-supervised learning primarily focus on natural language understanding tasks, whereas SSDS is a generative task with different summary possibilities per dialogue. The authors propose a novel scoring approach called SiCF, which assesses three key aspects: semantic invariance (model confidence), coverage (factual recall), and faithfulness (factual precision). By leveraging the SiCF score, they select high-quality generated summaries from unlabeled dialogues to train summarization models. Comprehensive experiments on three public datasets demonstrate the effectiveness of SiCF scores in uncertainty estimation and semi-supervised learning for dialogue summarization tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Semi-supervised dialogue summarization is a new way to improve how computers summarize conversations without needing as much human help. Right now, machines struggle to create good summaries because they don’t have enough labeled data (human-created examples). This research creates a special scoring system that looks at three important things: whether the model is confident in its summary, if it includes most of the important information, and how accurate the summary is. By using this score, computers can learn from conversations without labels to create better summaries. |
Keywords
» Artificial intelligence » Language understanding » Precision » Recall » Semi supervised » Summarization
