# Building a Production Model for Retrieval-Based Chatbots

## TL;DR

This paper presents a dual encoder architecture for retrieval-based chatbots that enables practical, scalable, and high-quality response suggestion suitable for production environments, validated on a large help desk dataset.

## Contribution

The paper introduces a scalable dual encoder model and methods for generating response whitelists, addressing practical deployment challenges in retrieval-based chatbots.

## Key findings

- Model achieves production-quality performance
- Dual encoder scales well with response whitelist size
- Human evaluation confirms effectiveness

## Abstract

Response suggestion is an important task for building human-computer conversation systems. Recent approaches to conversation modeling have introduced new model architectures with impressive results, but relatively little attention has been paid to whether these models would be practical in a production setting. In this paper, we describe the unique challenges of building a production retrieval-based conversation system, which selects outputs from a whitelist of candidate responses. To address these challenges, we propose a dual encoder architecture which performs rapid inference and scales well with the size of the whitelist. We also introduce and compare two methods for generating whitelists, and we carry out a comprehensive analysis of the model and whitelists. Experimental results on a large, proprietary help desk chat dataset, including both offline metrics and a human evaluation, indicate production-quality performance and illustrate key lessons about conversation modeling in practice.