相关论文: CommonForms: A Large, Diverse Dataset for Form Fie…

Query by Example is a well-known information retrieval task in which a document is chosen by the user as the search query and the goal is to retrieve relevant documents from a large collection. However, a document often covers multiple…

Despite significant progress in multimodal large language models (MLLMs), their performance on complex, multi-page document comprehension remains inadequate, largely due to the lack of high-quality, document-level datasets. While current…

With the rise of sophisticated scam websites that exploit human psychological vulnerabilities, distinguishing between legitimate and scam websites has become increasingly challenging. This paper presents ScamFerret, an innovative agent…

Current language understanding approaches focus on small documents, such as newswire articles, blog posts, product reviews and discussion forum entries. Understanding and extracting information from large documents like legal briefs,…

The automatic extraction of key-value information from handwritten documents is a key challenge in document analysis. A reliable extraction is a prerequisite for the mass digitization efforts of many archives. Large Vision Language Models…

This paper presents a new state-of-the-art for document image classification and retrieval, using features learned by deep convolutional neural networks (CNNs). In object and scene analysis, deep neural nets are capable of learning a…

Natural language inference (NLI) is formulated as a unified framework for solving various NLP problems such as relation extraction, question answering, summarization, etc. It has been studied intensively in the past few years thanks to the…

Even for a conservative estimate, 80% of enterprise data reside in unstructured files, stored in data lakes that accommodate heterogeneous formats. Classical search engines can no longer meet information seeking needs, especially when the…

Pattern spotting consists of searching in a collection of historical document images for occurrences of a graphical object using an image query. Contrary to object detection, no prior information nor predefined class is given about the…

Multimodal document understanding is a challenging task to process and comprehend large amounts of textual and visual information. Recent advances in Large Language Models (LLMs) have significantly improved the performance of this task.…

An important handicap of document analysis research is that documents tend to be copyrighted or contain private information, which prohibits their open publication and the creation of centralised, large-scale document datasets. Instead,…

We introduce the Scanning Single Shot Detector (ScanSSD) for locating math formulas offset from text and embedded in textlines. ScanSSD uses only visual features for detection: no formatting or typesetting information such as layout, font,…

Deep learning-based approaches for automatic document layout analysis and content extraction have the potential to unlock rich information trapped in historical documents on a large scale. One major hurdle is the lack of large datasets for…

Recent Large Language Models (LLMs) have demonstrated remarkable capabilities in generating text that closely resembles human writing across wide range of styles and genres. However, such capabilities are prone to potential abuse, such as…

PDF is one of the most prominent data formats, making PDF parsing crucial for information extraction and retrieval, particularly with the rise of RAG systems. While various PDF parsing tools exist, their effectiveness across different…

Document parsing (DP) transforms unstructured or semi-structured documents into structured, machine-readable representations, enabling downstream applications such as knowledge base construction and retrieval-augmented generation (RAG).…

Document-level natural language inference (DOCNLI) is a new challenging task in natural language processing, aiming at judging the entailment relationship between a pair of hypothesis and premise documents. Current datasets and baselines…

We present a resource for the task of FrameNet semantic frame disambiguation of over 5,000 word-sentence pairs from the Wikipedia corpus. The annotations were collected using a novel crowdsourcing approach with multiple workers per sentence…

Publication databases rely on accurate metadata extraction from diverse web sources, yet variations in web layouts and data formats present challenges for metadata providers. This paper introduces CRAWLDoc, a new method for contextual…

Audit transaction testing validates accuracy and completeness of customer-facing statements against internal systems of record. Traditional manual, sample-based review of unstructured PDF statements is labor-intensive and does not scale to…