Abstract: The disclosure herein describes a system for generating customizable summaries of multi-message conversations in email threads and other multi-message and multi-participant messaging applications. A summary icon is displayed if the number of messages in a thread exceeds a threshold number. Message data is cleaned and analyzed by ML models to generate feature vectors representing the messages content. Multiple loglinear regression models compute similarity between message sentences. Clustering algorithm(s) to generate a multi-message conversation thread summary based on the values. If the user selects the summary icon, the multi-message conversation thread summary is displayed. The summary includes summary sentences and/or annotations describing content of the messages in the thread, participants contributing to the messages in the thread, links back to the original messages in the thread and/or a count of the number of messages contributed by each participant.

Abstract: The disclosure herein describes a system for generating customizable summaries of multi-message conversations in email threads and other multi-message and multi-participant messaging applications. A summary icon is displayed if the number of messages in a thread exceeds a threshold number. Message data is cleaned and analyzed by ML models to generate feature vectors representing the messages content. Multiple loglinear regression models compute similarity between message sentences. Clustering algorithm(s) to generate a multi-message conversation thread summary based on the values. If the user selects the summary icon, the multi-message conversation thread summary is displayed. The summary includes summary sentences and/or annotations describing content of the messages in the thread, participants contributing to the messages in the thread, links back to the original messages in the thread and/or a count of the number of messages contributed by each participant.

Abstract: The disclosure herein describes a system for generating customizable summaries of multi-message conversations in email threads and other multi-message and multi-participant messaging applications. A summary icon is displayed if the number of messages in a thread exceeds a threshold number. Message data is cleaned and analyzed by ML models to generate feature vectors representing the messages content. Multiple loglinear regression models compute similarity between message sentences. Clustering algorithm(s) to generate a multi-message conversation thread summary based on the values. If the user selects the summary icon, the multi-message conversation thread summary is displayed. The summary includes summary sentences and/or annotations describing content of the messages in the thread, participants contributing to the messages in the thread, links back to the original messages in the thread and/or a count of the number of messages contributed by each participant.