Sorting email with natural language processing and conformal prediction

Patrizio Giovannotti, Daljit Rehal

Research output: Contribution to conferencePosterpeer-review

63 Downloads (Pure)

Abstract

Large companies receive thousands of email messages every day. Most of these messages come from their customers and must be forwarded to the right support agents, depending on the customer needs. This sorting procedure can be done manually, which is cost- and time-inefficient, or automatically using natural language processing (NLP) techniques. However, each wrong classification may result in a message being forwarded to the wrong agent, creating further costs. For this reason a reliable estimation of the classification confidence is required. This poster describes how Centrica combined Conformal Prediction and NLP to reliably classify the topic and sentiment of incoming email.
Original languageEnglish
Publication statusPublished - 29 Aug 2019
EventThe 8th Symposium on Conformal and Probabilistic Prediction with Applications: COPA 2019 - Golden Sands, Bulgaria
Duration: 9 Sept 201911 Sept 2019
http://clrc.rhul.ac.uk/copa2019/

Conference

ConferenceThe 8th Symposium on Conformal and Probabilistic Prediction with Applications: COPA 2019
Country/TerritoryBulgaria
CityGolden Sands
Period9/09/1911/09/19
Internet address

Keywords

  • natural language processing
  • conformal prediction

Cite this