TempoSum

LMS可以推廣到未來的數據嗎？關於文本摘要的經驗分析

該存儲庫包含本文的數據，LMS可以推廣到將來的數據嗎？關於文本摘要的經驗分析

 @inproceedings{temposum23,
    title="{Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization}",
    author = {Chi Seng Cheang and
                  Hou Pong Chan and
                  Derek F. Wong and
                  Xuebo Liu and
                  Zhaocong Li and
                  Yanming Sun and
                  Shudong Liu and
                  Lidia S. Chao},
    booktitle = "Proceedings of the Conference on Empirical Methods in Natural Language Processing ({EMNLP})",
    month = {December},
    year = "2023",
    publisher = "Association for Computational Linguistics",
    }

獲取數據

從HuggingFace數據集庫下載數據集

運行以下命令以從HuggingFace數據集庫加載數據集。

 import datasets

# BBC in-distribution test set
dataset = datasets . load_dataset ( 'chiseng-cheang/TempoSum' , 'BBC_in-distribution' )

# BBC future test set
dataset = datasets . load_dataset ( 'chiseng-cheang/TempoSum' , 'BBC_future' )

# CNN in-distribution test set
dataset = datasets . load_dataset ( 'chiseng-cheang/TempoSum' , 'CNN_in-distribution' )

# CNN future test set
dataset = datasets . load_dataset ( 'chiseng-cheang/TempoSum' , 'CNN_future' )

手動下載

所有數據集也可在以下網址找到：https：//drive.google.com/drive/folders/1bdetfqoea8gd240h78pgxbo68e53ea9e？ usp = sharing