Commentary Generation from Data Records of Multiplayer Strategy Esports Game

TL;DR

This paper introduces the task of automatically generating game commentaries from esports data records, creating a large dataset from League of Legends, and evaluating Transformer models for this purpose.

Contribution

It presents the first large-scale dataset for esports data-to-text generation and assesses Transformer-based models, highlighting challenges and potential for future research.

Findings

Transformer models show promise but face challenges in this task.

Pre-trained language models impact commentary quality.

Dataset release aims to foster further research.

Abstract

Esports, a sports competition on video games, has become one of the most important sporting events. Although esports play logs have been accumulated, only a small portion of them accompany text commentaries for the audience to retrieve and understand the plays. In this study, we therefore introduce the task of generating game commentaries from esports' data records. We first build large-scale esports data-to-text datasets that pair structured data and commentaries from a popular esports game, League of Legends. We then evaluate Transformer-based models to generate game commentaries from structured data records, while examining the impact of the pre-trained language models. Evaluation results on our dataset revealed the challenges of this novel task. We will release our dataset to boost potential research in the data-to-text generation community.