Introducing Spatial Information and a Novel Evaluation Scheme for Open-Domain Live Commentary Generation

Erica Kido Shimomoto, Edison Marrese-Taylor, Ichiro Kobayashi, Hiroya Takamura, Yusuke Miyao


Abstract
This paper focuses on the task of open-domain live commentary generation. Compared to domain-specific work in this task, this setting proved particularly challenging due to the absence of domain-specific features. Aiming to bridge this gap, we integrate spatial information by proposing an utterance generation model with a novel spatial graph that is flexible to deal with the open-domain characteristics of the commentaries and significantly improves performance. Furthermore, we propose a novel evaluation scheme, more suitable for live commentary generation, that uses LLMs to automatically check whether generated utterances address essential aspects of the video via the answerability of questions extracted directly from the videos using LVLMs. Our results suggest that using a combination of our answerability score and a standard machine translation metric is likely a more reliable way to evaluate the performance in this task.
Anthology ID:
2024.findings-emnlp.606
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10352–10370
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-emnlp.606/
DOI:
10.18653/v1/2024.findings-emnlp.606
Bibkey:
Cite (ACL):
Erica Kido Shimomoto, Edison Marrese-Taylor, Ichiro Kobayashi, Hiroya Takamura, and Yusuke Miyao. 2024. Introducing Spatial Information and a Novel Evaluation Scheme for Open-Domain Live Commentary Generation. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10352–10370, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Introducing Spatial Information and a Novel Evaluation Scheme for Open-Domain Live Commentary Generation (Shimomoto et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-emnlp.606.pdf