Unsupervised paradigm for information extraction from transcripts using BERT
This addresses the challenge of information extraction in industry settings where labeled data is scarce, though it is incremental as it applies existing BERT models to a specific domain.
The paper tackles the problem of extracting key topics and intents from noisy audio call transcripts without tagged data, using unsupervised BERT-based methods, achieving near-human accuracy in evaluation.
Audio call transcripts are one of the valuable sources of information for multiple downstream use cases such as understanding the voice of the customer and analyzing agent performance. However, these transcripts are noisy in nature and in an industry setting, getting tagged ground truth data is a challenge. In this paper, we present a solution implemented in the industry using BERT Language Models as part of our pipeline to extract key topics and multiple open intents discussed in the call. Another problem statement we looked at was the automatic tagging of transcripts into predefined categories, which traditionally is solved using supervised approach. To overcome the lack of tagged data, all our proposed approaches use unsupervised methods to solve the outlined problems. We evaluate the results by quantitatively comparing the automatically extracted topics, intents and tagged categories with human tagged ground truth and by qualitatively measuring the valuable concepts and intents that are not present in the ground truth. We achieved near human accuracy in extraction of these topics and intents using our novel approach