@inproceedings{dcc1c24ca5bc4a0d90a8578067fd9464,
title = "ACL TA-DA: A Dataset for Text Summarization and Generation",
abstract = "Selecting appropriate natural language datasets is imperative to achieving good performance in deep learning natural language tasks. Recent state-of-the-art language models train huge corpora to achieving high language understanding performances. Also, to conduct diverse NLP tasks, fine-tuning pre-trained language models with task specific datasets is necessary. In this paper, we introduce ACL TA-DA (Association of Computational Linguistics Titles Abstracts DAta) consisting of 22k English titles and corresponding abstracts of papers published in ACL. Two NLP tasks, (1) text summarization and (2) text generation, are suitable tasks for our ACL TA-DA dataset. We train and report results from several state-of-the-art text summarization and generation models with our dataset to demonstrate that our dataset can be widely applied.",
keywords = "data collection, natural language generation, text summarization",
author = "Park, \{Min Su\} and Eunil Park",
note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 38th Annual ACM Symposium on Applied Computing, SAC 2023 ; Conference date: 27-03-2023 Through 31-03-2023",
year = "2023",
month = mar,
day = "27",
doi = "10.1145/3555776.3577736",
language = "English",
series = "Proceedings of the ACM Symposium on Applied Computing",
publisher = "Association for Computing Machinery",
pages = "1233--1239",
booktitle = "Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing, SAC 2023",
}