Extractive Summarization of Call Transcripts
This addresses the need for better summarization of customer service call transcripts, but it is incremental as it builds on existing techniques like topic modeling.
The paper tackled the problem of summarizing call transcripts, which are often poorly punctuated, by developing a method that combines topic modeling, sentence selection, and punctuation restoration to produce more readable summaries, with extensive testing demonstrating its efficacy.
Text summarization is the process of extracting the most important information from the text and presenting it concisely in fewer sentences. Call transcript is a text that involves textual description of a phone conversation between a customer (caller) and agent(s) (customer representatives). This paper presents an indigenously developed method that combines topic modeling and sentence selection with punctuation restoration in condensing ill-punctuated or un-punctuated call transcripts to produce summaries that are more readable. Extensive testing, evaluation and comparisons have demonstrated the efficacy of this summarizer for call transcript summarization.