A Semi-supervised Multi-task Learning Approach to Classify Customer Contact Intents

06/10/2021
by   Li Dong, et al.
0

In the area of customer support, understanding customers' intents is a crucial step. Machine learning plays a vital role in this type of intent classification. In reality, it is typical to collect confirmation from customer support representatives (CSRs) regarding the intent prediction, though it can unnecessarily incur prohibitive cost to ask CSRs to assign existing or new intents to the mis-classified cases. Apart from the confirmed cases with and without intent labels, there can be a number of cases with no human curation. This data composition (Positives + Unlabeled + multiclass Negatives) creates unique challenges for model development. In response to that, we propose a semi-supervised multi-task learning paradigm. In this manuscript, we share our experience in building text-based intent classification models for a customer support service on an E-commerce website. We improve the performance significantly by evolving the model from multiclass classification to semi-supervised multi-task learning by leveraging the negative cases, domain- and task-adaptively pretrained ALBERT on customer contact texts, and a number of un-curated data with no labels. In the evaluation, the final model boosts the average AUC ROC by almost 20 points compared to the baseline finetuned multiclass classification ALBERT model.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/01/2018

Seq2Seq and Multi-Task Learning for joint intent and content extraction for domain specific interpreters

This study evaluates the performances of an LSTM network for detecting a...
research
08/11/2020

HydraMix-Net: A Deep Multi-task Semi-supervised Learning Approach for Cell Detection and Classification

Semi-supervised techniques have removed the barriers of large scale labe...
research
08/05/2020

TPG-DNN: A Method for User Intent Prediction Based on Total Probability Formula and GRU Loss with Multi-task Learning

The E-commerce platform has become the principal battleground where peop...
research
01/23/2022

Dichotomic Pattern Mining with Applications to Intent Prediction from Semi-Structured Clickstream Datasets

We introduce a pattern mining framework that operates on semi-structured...
research
06/15/2023

Knowledge Assembly: Semi-Supervised Multi-Task Learning from Multiple Datasets with Disjoint Labels

In real-world scenarios we often need to perform multiple tasks simultan...
research
11/01/2018

Helping each Other: A Framework for Customer-to-Customer Suggestion Mining using a Semi-supervised Deep Neural Network

Suggestion mining is increasingly becoming an important task along with ...
research
10/26/2022

End-to-End Speech to Intent Prediction to improve E-commerce Customer Support Voicebot in Hindi and English

Automation of on-call customer support relies heavily on accurate and ef...

Please sign up or login with your details

Forgot password? Click here to reset