arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.03553cs.CLcs.AIcs.IRcs.LG
收藏

Summaformers @ LaySumm 20,LongSumm 20

Summaformers @ LaySumm 20, LongSumm 20

Microsoft(微软);International Institute of Information Technology, Hyderabad(海得拉巴国际信息技术学院)

Sayar Ghosh Roy, Nikhil Pinnaparaju, Risubh Jain, Manish Gupta, Vasudeva Varma

摘要:

自动文摘作为自然语言处理的一项重要任务,得到了广泛的研究。传统上,已经提出了各种基于特征工程和机器学习的系统用于提取和抽象文本摘要。最近,基于深度学习,特别是基于transformer的系统非常流行。摘要是一项具有认知挑战性的任务-提取有摘要价值的句子是费力的,并且在进行抽象摘要时简短地表达语义是复杂的。在本文中,我们专门研究了多个领域的科研论文的摘要问题。我们区分了两种类型的摘要,即(a)LaySumm:一种非常简短的摘要,以外行的方式捕捉研究论文的本质,限制明显特定的技术术语,以及(b)LongSumm:一种更长更详细的摘要,旨在提供对论文中涉及的各种想法的具体见解。在利用最新的基于Transformer的模型的同时,我们的系统简单、直观,并且基于特定的纸张部分如何对上述两种类型的人类摘要做出贡献。使用ROUGE指标对金标准摘要的评估证明了我们的方法的有效性。在盲测语料库中,我们的系统分别在LongSumm和LaySumm任务中排名第一和第三。

英文摘要:

Automatic text summarization has been widely studied as an important task in natural language processing. Traditionally, various feature engineering and machine learning based systems have been proposed for extractive as well as abstractive text summarization. Recently, deep learning based, specifically Transformer-based systems have been immensely popular. Summarization is a cognitively challenging task - extracting summary worthy sentences is laborious, and expressing semantics in brief when doing abstractive summarization is complicated. In this paper, we specifically look at the problem of summarizing scientific research papers from multiple domains. We differentiate between two types of summaries, namely, (a) LaySumm: A very short summary that captures the essence of the research paper in layman terms restricting overtly specific technical jargon and (b) LongSumm: A much longer detailed summary aimed at providing specific insights into various ideas touched upon in the paper. While leveraging latest Transformer-based models, our systems are simple, intuitive and based on how specific paper sections contribute to human summaries of the two types described above. Evaluations against gold standard summaries using ROUGE metrics prove the effectiveness of our approach. On blind test corpora, our system ranks first and third for the LongSumm and LaySumm tasks respectively.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑