Heuristic-based Inter-training to Improve Few-shot Multi-perspective Dialog Summarization

TL;DR

This paper introduces a heuristic-based inter-training method that enhances multi-perspective dialog summarization with minimal annotated data, significantly reducing the need for extensive manual labeling.

Contribution

The work proposes a novel inter-training approach leveraging heuristics to generate weak labels, enabling effective multi-perspective summarization with scarce annotated data.

Findings

Achieves 94% of the performance of fully supervised models using only 7% of training data.

Supports multi-perspective summarization with minimal annotated data.

Demonstrates the effectiveness of heuristic-based weak supervision in dialog summarization.

Abstract

Many organizations require their customer-care agents to manually summarize their conversations with customers. These summaries are vital for decision making purposes of the organizations. The perspective of the summary that is required to be created depends on the application of the summaries. With this work, we study the multi-perspective summarization of customer-care conversations between support agents and customers. We observe that there are different heuristics that are associated with summaries of different perspectives, and explore these heuristics to create weak-labeled data for intermediate training of the models before fine-tuning with scarce human annotated summaries. Most importantly, we show that our approach supports models to generate multi-perspective summaries with a very small amount of annotated data. For example, our approach achieves 94\% of the performance (Rouge-2) of a model trained with the original data, by training only with 7\% of the original data.