LLM aided semi-supervision for efficient Extractive Dialog Summarization

Nishant Mishra, Gaurav Sahu, Iacer Calixto, Ameen Abu-Hanna, Issam Laradji


Abstract
Generating high-quality summaries for chat dialogs often requires large labeled datasets. We propose a method to efficiently use unlabeled data for extractive summarization of customer-agent dialogs. In our method, we frame summarization as a question-answering problem and use state-of-the-art large language models (LLMs) to generate pseudo-labels for a dialog. We then use these pseudo-labels to fine-tune a chat summarization model, effectively transferring knowledge from the large LLM into a smaller specialized model. We demonstrate our method on the TWEETSUMM dataset, and show that using 10% of the original labelled data set we can achieve 65.9/57.0/61.0 ROUGE-1/-2/-L, whereas the current state-of-the-art trained on the entire training data set obtains 65.16/55.81/64.37 ROUGE-1/-2/-L. In other words, in the worst case (i.e., ROUGE-L) we still effectively retain 94.7% of the performance while using only 10% of the data.
Anthology ID:
2023.findings-emnlp.670
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10002–10009
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.670
DOI:
10.18653/v1/2023.findings-emnlp.670
Bibkey:
Cite (ACL):
Nishant Mishra, Gaurav Sahu, Iacer Calixto, Ameen Abu-Hanna, and Issam Laradji. 2023. LLM aided semi-supervision for efficient Extractive Dialog Summarization. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10002–10009, Singapore. Association for Computational Linguistics.
Cite (Informal):
LLM aided semi-supervision for efficient Extractive Dialog Summarization (Mishra et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.670.pdf