A modular approach for multimodal summarization of TV shows

L Mahon, M Lapata - arxiv preprint arxiv:2403.03823, 2024 - arxiv.org
In this paper we address the task of summarizing television shows, which touches key areas
in AI research: complex reasoning, multiple modalities, and long narratives. We present a …

Unveiling the essence of poetry: Introducing a comprehensive dataset and benchmark for poem summarization

R Mahbub, I Khan, S Anuva, MS Shahriar… - Proceedings of the …, 2023 - aclanthology.org
While research in natural language processing has progressed significantly in creative
language generation, the question of whether language models can interpret the intended …

Screenwriter: Automatic screenplay generation and movie summarisation

L Mahon, M Lapata - arxiv preprint arxiv:2410.19809, 2024 - arxiv.org
The proliferation of creative video content has driven demand for textual descriptions or
summaries that allow users to recall key plot points or get an overview without watching. The …

Select and summarize: Scene saliency for movie script summarization

R Saxena, F Keller - arxiv preprint arxiv:2404.03561, 2024 - arxiv.org
Abstractive summarization for long-form narrative texts such as movie scripts is challenging
due to the computational and memory constraints of current language models. A movie …

Fine-Tuned LLMs are" Time Capsules" for Tracking Societal Bias Through Books

S Madhusudan, R Morabito, S Reid, NG Sadr… - arxiv preprint arxiv …, 2025 - arxiv.org
Books, while often rich in cultural insights, can also mirror societal biases of their eras-
biases that Large Language Models (LLMs) may learn and perpetuate during training. We …