Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learning

03/23/2021
by   Sonal Garg, et al.
0

Customer support via chat requires agents to resolve customer queries with minimum wait time and maximum customer satisfaction. Given that the agents as well as the customers can have varying levels of literacy, the overall quality of responses provided by the agents tend to be poor if they are not predefined. But using only static responses can lead to customer detraction as the customers tend to feel that they are no longer interacting with a human. Hence, it is vital to have variations of the static responses to reduce monotonicity of the responses. However, maintaining a list of such variations can be expensive. Given the conversation context and the agent response, we propose an unsupervised frame-work to generate contextual paraphrases using autoregressive models. We also propose an automated metric based on Semantic Similarity, Textual Entailment, Expression Diversity and Fluency to evaluate the quality of contextual paraphrases and demonstrate performance improvement with Reinforcement Learning (RL) fine-tuning using the automated metric as the reward function.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/26/2018

Beyond "How may I help you?": Assisting Customer Service Agents with Proactive Responses

We study the problem of providing recommended responses to customer serv...
research
09/04/2021

Effective user intent mining with unsupervised word representation models and topic modelling

Understanding the intent behind chat between customers and customer serv...
research
11/15/2017

Detecting Egregious Conversations between Customers and Virtual Agents

Virtual agents are becoming a prominent channel of interaction in custom...
research
06/08/2023

The economic trade-offs of large language models: A case study

Contacting customer service via chat is a common practice. Because emplo...
research
12/24/2022

Linguistic Elements of Engaging Customer Service Discourse on Social Media

Customers are rapidly turning to social media for customer support. Whil...
research
06/11/2020

Surveys without Questions: A Reinforcement Learning Approach

The 'old world' instrument, survey, remains a tool of choice for firms t...
research
02/24/2019

AgentBuddy: A Contextual Bandit based Decision Support System for Customer Support Agents

In this short paper, we present early insights from a Decision Support S...

Please sign up or login with your details

Forgot password? Click here to reset