Auto-tagging of Short Conversational Sentences using Transformer Methods

TL;DR

This paper explores transformer-based models, including BERT and GPT-2, for accurately categorizing short conversational sentences into 46 categories in Turkish, aiming to improve chat application responses.

Contribution

It introduces a dataset of Turkish chat sentences classified into 46 categories and evaluates multiple transformer models for automatic tagging accuracy.

Findings

BERT models achieved high classification accuracy.

GPT-2 model performed competitively in Turkish sentence tagging.

Transformer models outperformed traditional methods in this task.

Abstract

The problem of categorizing short speech sentences according to their semantic features with high accuracy is a subject studied in natural language processing. In this study, a data set created with samples classified in 46 different categories was used. Examples consist of sentences taken from chat conversations between a company's customer representatives and the company's website visitors. The primary purpose is to automatically tag questions and requests from visitors in the most accurate way for 46 predetermined categories for use in a chat application to generate meaningful answers to the questions asked by the website visitors. For this, different BERT models and one GPT-2 model, pre-trained in Turkish, were preferred. The classification performances of the relevant models were analyzed in detail and reported accordingly.