Unsupervised paradigm for information extraction from transcripts using BERT

TL;DR

This paper introduces an unsupervised approach using BERT models to extract key topics and intents from noisy call transcripts, achieving near human-level accuracy without relying on labeled data.

Contribution

It presents a novel unsupervised method leveraging BERT for information extraction from transcripts, overcoming the challenge of lacking annotated data.

Findings

Achieved near human accuracy in topic and intent extraction

Effectively extracted valuable concepts not present in ground truth

Demonstrated robustness on industry call transcript data

Abstract

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