arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.11289cs.CL
收藏

文本摘要系统综述:从统计方法到大型语言模型

A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models

University of Hawaii, Manoa(夏威夷大学马诺阿分校);University of Illinois at Chicago(伊利诺伊大学芝加哥分校);University of California, Davis(加州大学戴维斯分校)

Haopeng Zhang, Philip S. Yu, Jiawei Zhang

AI总结:

本文系统综述文本摘要从统计方法、深度学习、PLM 微调到 LLM 时代的演进,梳理数据集、指标、方法、基准与评估,并指出开放挑战和未来方向。

摘要:

随着深度神经网络、预训练语言模型(PLM)以及近期大型语言模型(LLM)的出现,文本摘要研究经历了数次重大转型。因此,本综述透过这些范式转变的视角,全面回顾文本摘要的研究进展与演进。全文分为两个主要部分:(1)详细概述 LLM 时代之前的数据集、评估指标和摘要方法,涵盖传统统计方法、深度学习方法以及 PLM 微调技术;(2)首次细致考察 LLM 时代在摘要的基准测试、建模和评估方面的最新进展。通过综合现有文献并给出连贯的总体梳理,本综述还讨论了研究趋势和开放挑战,并提出有前景的摘要研究方向,旨在帮助研究人员把握不断演变的摘要研究格局。

英文摘要:

Text summarization research has undergone several significant transformations with the advent of deep neural networks, pre-trained language models (PLMs), and recent large language models (LLMs). This survey thus provides a comprehensive review of the research progress and evolution in text summarization through the lens of these paradigm shifts. It is organized into two main parts: (1) a detailed overview of datasets, evaluation metrics, and summarization methods before the LLM era, encompassing traditional statistical methods, deep learning approaches, and PLM fine-tuning techniques, and (2) the first detailed examination of recent advancements in benchmarking, modeling, and evaluating summarization in the LLM era. By synthesizing existing literature and presenting a cohesive overview, this survey also discusses research trends, open challenges, and proposes promising research directions in summarization, aiming to guide researchers through the evolving landscape of summarization research.

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。

↑