English
Related papers

Related papers: A Benchmark of PDF Information Extraction Tools us…

200 papers

Procedures are an important knowledge component of documents that can be leveraged by cognitive assistants for automation, question-answering or driving a conversation. It is a challenging problem to parse big dense documents like product…

Artificial Intelligence · Computer Science 2020-10-21 Shivali Agarwal , Shubham Atreja , Vikas Agarwal

Unstructured data formats account for over 80% of the data currently stored, and extracting value from such formats remains a considerable challenge. In particular, current approaches for managing unstructured documents do not support…

In the rapidly evolving field of data science, efficiently navigating the expansive body of academic literature is crucial for informed decision-making and innovation. This paper presents an enhanced Retrieval-Augmented Generation (RAG)…

Information Retrieval · Computer Science 2025-05-15 Ahmet Yasin Aytar , Kemal Kilic , Kamer Kaya

With the development of Internet technology, the phenomenon of information overload is becoming more and more obvious. It takes a lot of time for users to obtain the information they need. However, keyphrases that summarize document…

Information Retrieval · Computer Science 2021-12-01 Chengzhi Zhang , Lei Zhao , Mengyuan Zhao , Yingyi Zhang

Automatic extraction of procedural graphs from documents creates a low-cost way for users to easily understand a complex procedure by skimming visual graphs. Despite the progress in recent studies, it remains unanswered: whether the…

Computation and Language · Computer Science 2024-08-09 Weihong Du , Wenrui Liao , Hongru Liang , Wenqiang Lei

Delivering high-quality content is crucial for effective reading comprehension and successful learning. Ensuring educational materials are interpreted as intended by their authors is a persistent challenge, especially with the added…

Computers and Society · Computer Science 2024-12-17 Madjid Sadallah

Learned representations of scientific documents can serve as valuable input features for downstream tasks without further fine-tuning. However, existing benchmarks for evaluating these representations fail to capture the diversity of…

Computation and Language · Computer Science 2023-11-14 Amanpreet Singh , Mike D'Arcy , Arman Cohan , Doug Downey , Sergey Feldman

Automatically extracted metadata from scholarly documents in PDF formats is usually noisy and heterogeneous, often containing incomplete fields and erroneous values. One common way of cleaning metadata is to use a bibliographic reference…

Digital Libraries · Computer Science 2019-06-21 Athar Sefid , Jian Wu , Allen C. Ge , Jing Zhao , Lu Liu , Cornelia Caragea , Prasenjit Mitra , C. Lee Giles

Many documents, that we call templatized documents, are programmatically generated by populating fields in a visual template. Effective data extraction from these documents is crucial to supporting downstream analytical tasks. Current data…

Databases · Computer Science 2025-01-14 Yiming Lin , Mawil Hasan , Rohan Kosalge , Alvin Cheung , Aditya G. Parameswaran

We introduce VAREX (VARied-schema EXtraction), a benchmark for evaluating multimodal foundation models on structured data extraction from government forms. VAREX employs a Reverse Annotation pipeline that programmatically fills PDF…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Udi Barzelay , Ophir Azulai , Inbar Shapira , Idan Friedman , Foad Abo Dahood , Madison Lee , Abraham Daniels

Recent years in NLP have seen the continued development of domain-specific information extraction tools for scientific documents, alongside the release of increasingly multimodal pretrained transformer models. While the opportunity for…

Computation and Language · Computer Science 2025-06-25 Sireesh Gururaja , Yueheng Zhang , Guannan Tang , Tianhao Zhang , Kevin Murphy , Yu-Tsen Yi , Junwon Seo , Anthony Rollett , Emma Strubell

Extracting top-k keywords and documents using weighting schemes are popular techniques employed in text mining and machine learning for different analysis and retrieval tasks. The weights are usually computed in the data preprocessing step,…

Databases · Computer Science 2021-08-23 Ciprian-Octavian Truica , Elena Apostol , Jérôme Darmont , Ira Assent

Pool of knowledge available to the mankind depends on the source of learning resources, which can vary from ancient printed documents to present electronic material. The rapid conversion of material available in traditional libraries to…

Computer Vision and Pattern Recognition · Computer Science 2014-12-25 Akmal Jahan Mac , Roshan G Ragel

With the recent developments in digitisation, there are increasing number of documents available online. There are several information extraction tools that are available to extract information from digitised documents. However, identifying…

Information Retrieval · Computer Science 2021-11-08 Richi Nayak , Thirunavukarasu Balasubramaniam , Sangeetha Kutty , Sachindra Banduthilaka , Erin Peterson

Large language models (LLMs) have demonstrated remarkable capabilities in text analysis tasks, yet their evaluation on complex, real-world applications remains challenging. We define a set of tasks, Multi-Insight Multi-Document Extraction…

Computation and Language · Computer Science 2024-12-02 John Francis , Saba Esnaashari , Anton Poletaev , Sukankana Chakraborty , Youmna Hashem , Jonathan Bright

Requirements identification in textual documents or extraction is a tedious and error prone task that many researchers suggest automating. We manually annotated the PURE dataset and thus created a new one containing both requirements and…

Software Engineering · Computer Science 2022-02-07 Vladimir Ivanov , Andrey Sadovykh , Alexandr Naumchev , Alessandra Bagnato , Kirill Yakovlev

The past year has seen over 20 open-source document parsing models, yet thefield still benchmarks almost exclusively on OmniDocBench, a 1,355-pagemanually annotated dataset whose top scores have saturated above 90%. Athree-stage audit…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Zhiheng Li , Zongyang Ma , Jiaxian Chen , Jianing Zhang , Zhaolong Su , Yutong Zhang , Zhiyin Yu , Ruiqi Liu , Xiaolei Lv , Bo Li , Jun Gao , Ziqi Zhang , Chunfeng Yuan , Bing Li , Weiming Hu

In this era of information technology, abundant information is available on the internet in the form of web pages and documents on any given topic. Finding the most relevant and informative content out of these huge number of documents,…

Computers and Society · Computer Science 2023-12-21 Uswa Ihsan , Humaira Ashraf , NZ Jhanjhi

Document indexation is an essential task achieved by archivists or automatic indexing tools. To retrieve relevant documents to a query, keywords describing this document have to be carefully chosen. Archivists have to find out the right…

Information Retrieval · Computer Science 2009-12-09 Carlo Abi Chahine , Nathalie Chaignaud , Jean-Philippe Kotowicz , Jean-Pierre Pécuchet

The abundance of the data in the Internet facilitates the improvement of extraction and processing tools. The trend in the open data publishing encourages the adoption of structured formats like CSV and RDF. However, there is still a…

Information Retrieval · Computer Science 2016-08-08 Mikhail Galkin , Dmitry Mouromtsev , Sören Auer