Heuristic-based Inter-training to Improve Few-shot Multi-perspective Dialog Summarization
This addresses the need for efficient summarization in customer-care settings where manual summarization is costly and perspective-specific summaries are required, though it is incremental as it builds on existing few-shot learning methods.
The paper tackles the problem of generating multi-perspective summaries from customer-care conversations with limited annotated data by using heuristics to create weak-labeled data for intermediate training, achieving 94% of the performance of a model trained with full data using only 7% of the data.
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.