Auto-tagging of Short Conversational Sentences using Natural Language Processing Methods

TL;DR

This paper develops and compares transformer-based models for auto-tagging short conversational sentences in a specific domain, aiming to enhance chatbot dialogue generation.

Contribution

It introduces a dataset of manually tagged conversational sentences and evaluates multiple models, achieving the best results with BERT for domain-specific auto-tagging.

Findings

BERT outperforms other models in auto-tagging accuracy

Manually tagged dataset of 14,000 sentences created for this task

Models are publicly available for replication and further research

Abstract

In this study, we aim to find a method to auto-tag sentences specific to a domain. Our training data comprises short conversational sentences extracted from chat conversations between company's customer representatives and web site visitors. We manually tagged approximately 14 thousand visitor inputs into ten basic categories, which will later be used in a transformer-based language model with attention mechanisms for the ultimate goal of developing a chatbot application that can produce meaningful dialogue. We considered three different state-of-the-art models and reported their auto-tagging capabilities. We achieved the best performance with the bidirectional encoder representation from transformers (BERT) model. Implementation of the models used in these experiments can be cloned from our GitHub repository and tested for similar auto-tagging problems without much effort.