中文
相关论文

相关论文: "What is the value of {templates}?" Rethinking Doc…

200 篇论文

Key Information Extraction (KIE) is aimed at extracting structured information (e.g. key-value pairs) from form-style documents (e.g. invoices), which makes an important step towards intelligent document understanding. Previous approaches…

人工智能 · 计算机科学 2022-06-15 Fengbin Zhu , Chao Wang , Wenqiang Lei , Ziyang Liu , Tat Seng Chua

Advances in the Visually-rich Document Understanding (VrDU) field and particularly the Key-Information Extraction (KIE) task are marked with the emergence of efficient Transformer-based approaches such as the LayoutLM models. Despite the…

计算与语言 · 计算机科学 2023-05-01 Seif Laatiri , Pirashanth Ratnamogan , Joel Tang , Laurent Lam , William Vanhuffel , Fabien Caspani

Understanding visually-rich business documents to extract structured data and automate business workflows has been receiving attention both in academia and industry. Although recent multi-modal language models have achieved impressive…

计算与语言 · 计算机科学 2023-09-19 Zilong Wang , Yichao Zhou , Wei Wei , Chen-Yu Lee , Sandeep Tata

Key Information Extraction (KIE) underpins the understanding of visual documents (e.g., receipts and contracts) by extracting precise semantic content and accurately capturing spatial structure. Yet existing multimodal large language models…

计算机视觉与模式识别 · 计算机科学 2025-07-15 Son Nguyen , Giang Nguyen , Hung Dao , Thao Do , Daeyoung Kim

Document Key Information Extraction (KIE) is a technology that transforms valuable information in document images into structured data, and it has become an essential function in industrial settings. However, current evaluation metrics of…

计算与语言 · 计算机科学 2025-03-27 Minsoo Khang , Sang Chul Jung , Sungrae Park , Teakgyu Hong

In recent years, the challenge of extracting information from business documents has emerged as a critical task, finding applications across numerous domains. This effort has attracted substantial interest from both industry and academy,…

Relevance evaluation of a query and a passage is essential in Information Retrieval (IR). Recently, numerous studies have been conducted on tasks related to relevance judgment using Large Language Models (LLMs) such as GPT-4, demonstrating…

信息检索 · 计算机科学 2024-05-14 Jaekeol Choi

Enterprise documents, such as forms and reports, embed critical information for downstream applications like data archiving, automated workflows, and analytics. Although generalist Vision Language Models (VLMs) perform well on established…

计算与语言 · 计算机科学 2026-02-13 Mathieu Sibue , Andres Muñoz Garza , Samuel Mensah , Pranav Shetty , Zhiqiang Ma , Xiaomo Liu , Manuela Veloso

Document-based Question-Answering (QA) tasks are crucial for precise information retrieval. While some existing work focus on evaluating large language models performance on retrieving and answering questions from documents, assessing the…

Information Extraction (IE) researchers are mapping tasks to Question Answering (QA) in order to leverage existing large QA resources, and thereby improve data efficiency. Especially in template extraction (TE), mapping an ontology to a set…

计算与语言 · 计算机科学 2022-05-26 Nils Holzenberger , Yunmo Chen , Benjamin Van Durme

Large language models (LLMs) have achieved remarkable success in contextual knowledge understanding. In this paper, we show that these concentrated massive values consistently emerge in specific regions of attention queries (Q) and keys (K)…

计算与语言 · 计算机科学 2025-05-22 Mingyu Jin , Kai Mei , Wujiang Xu , Mingjie Sun , Ruixiang Tang , Mengnan Du , Zirui Liu , Yongfeng Zhang

Key Information Extraction (KIE) from real-world documents remains challenging due to substantial variations in layout structures, visual quality, and task-specific information requirements. Recent Large Multimodal Models (LMMs) have shown…

计算机视觉与模式识别 · 计算机科学 2026-04-27 Yifan Ji , Zhipeng Xu , Zhenghao Liu , Zulong Chen , Qian Zhang , Zhibo Yang , Junyang Lin , Yu Gu , Ge Yu , Maosong Sun

Augmenting large language models (LLMs) with user-specific knowledge is crucial for real-world applications, such as personal AI assistants. However, LLMs inherently lack mechanisms for prompt-driven knowledge capture. This paper…

计算与语言 · 计算机科学 2024-02-02 Tolga Çöplü , Arto Bendiken , Andrii Skomorokhov , Eduard Bateiko , Stephen Cobb , Joshua J. Bouw

Vision-Language Models (VLMs) have made remarkable progress in document-based Visual Question Answering (i.e., responding to queries about the contents of an input document provided as an image). In this work, we show these models can…

计算机视觉与模式识别 · 计算机科学 2024-07-12 Francesco Pinto , Nathalie Rauschmayr , Florian Tramèr , Philip Torr , Federico Tombari

With the advent of artificial intelligence (AI), many researchers are attempting to extract structured information from document-level biomedical literature by fine-tuning large language models (LLMs). However, they face significant…

神经与进化计算 · 计算机科学 2026-02-26 Lei Zhao , Ling Kang , Quan Guo

Visual document understanding (VDU) is a challenging task that involves understanding documents across various modalities (text and image) and layouts (forms, tables, etc.). This study aims to enhance generalizability of small VDU models by…

计算机视觉与模式识别 · 计算机科学 2024-10-07 Sungnyun Kim , Haofu Liao , Srikar Appalaraju , Peng Tang , Zhuowen Tu , Ravi Kumar Satzoda , R. Manmatha , Vijay Mahadevan , Stefano Soatto

Research in Document Intelligence and especially in Document Key Information Extraction (DocKIE) has been mainly solved as Token Classification problem. Recent breakthroughs in both natural language processing (NLP) and computer vision…

计算与语言 · 计算机科学 2023-04-24 Laurent Lam , Pirashanth Ratnamogan , Joël Tang , William Vanhuffel , Fabien Caspani

Instruction-tuned large language models (LLMs) employ structured templates, such as role markers and special tokens, to enforce format consistency during inference. However, we identify a critical limitation of such formatting: it induces a…

计算与语言 · 计算机科学 2025-05-27 Longfei Yun , Chenyang An , Zilong Wang , Letian Peng , Jingbo Shang

The field of visually rich document understanding (VRDU) aims to solve a multitude of well-researched NLP tasks in a multi-modal domain. Several datasets exist for research on specific tasks of VRDU such as document classification (DC), key…

Building document-grounded dialogue systems have received growing interest as documents convey a wealth of human knowledge and commonly exist in enterprises. Wherein, how to comprehend and retrieve information from documents is a…

计算与语言 · 计算机科学 2022-07-15 Zhenyu Zhang , Bowen Yu , Haiyang Yu , Tingwen Liu , Cheng Fu , Jingyang Li , Chengguang Tang , Jian Sun , Yongbin Li
‹ 上一页 1 2 3 10 下一页 ›