Hang Su, Hwanjun Song, Saab Mansour, Jianfeng He, Igor Shalyminov, Jason Cai
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Semi-supervised dialogue summarization (SSDS) leverages model-generated summaries to reduce reliance on human-labeled data and improve the performance of summarization models. While addressing label noise, previous works on semi-supervised learning primarily focus on natural language understanding tasks, assuming each sample has a unique label. However, these methods are not directly applicable to SSDS, as it is a generative task, and each dialogue can be summarized in different ways. In this work, we propose a novel scoring approach, SiCF, which encapsulates three primary dimensions of summarization model quality: Semantic invariance (indicative of model confidence), Coverage (factual recall), and Faithfulness (factual precision). Using the SiCF score, we select unlabeled dialogues with high-quality generated summaries 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. Our code is available at https: //github.com/amazon-science/ summarization-sicf-score. Pete: wanna go see the crimes of grindelwald? Ann: Oh , I saw it yesterday, sorry . . . ... Ann: Oh , it was OK but I think I liked the first part better. (1). Pete and Ann saw the crimes of grindelwald yesterday. (2). Ann saw... yesterday. She liked the first part better. (k). Ann saw the crimes of grindelwald yesterday.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2403.04073")
get_code_for_paper("2403.04073")
have("2403.04073")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2403.04073.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2403.04073)
Connect an agent — have() is free.