Related papers: Benchmarking Table Extraction from Heterogeneous S…

Automating information extraction from form-like documents at scale is a pressing need due to its potential impact on automating business workflows across many industries like financial services, insurance, and healthcare. The key challenge…

Extracting information from full documents is an important problem in many domains, but most previous work focus on identifying relationships within a sentence or a paragraph. It is challenging to create a large-scale information extraction…

Relation extraction (RE) aims to identify the semantic relations between named entities in text. Recent years have witnessed it raised to the document level, which requires complex reasoning with entities and mentions throughout an entire…

Table Detection (TD) is a fundamental task to enable visually rich document understanding, which requires the model to extract information without information loss. However, popular Intersection over Union (IoU) based evaluation metrics and…

We present a hierarchical convolutional document model with an architecture designed to support introspection of the document structure. Using this model, we show how to use visualisation techniques from the computer vision literature to…

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…

In our work, we propose to represent HTM as a set of flat models, or layers, and a set of topical hierarchies, or edges. We suggest several quality measures for edges of hierarchical models, resembling those proposed for flat models. We…

Benchmarking drug efficacy is a critical step in clinical trial design and planning. The challenge is that much of the data on efficacy endpoints is stored in scientific papers in free text form, so extraction of such data is currently a…

Document parsing converts visually rich documents into machine-readable structured representations, forming a crucial foundation for information systems. Although many benchmarks have been proposed for document parsing, they remain…

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…

Joint entity and relation extraction (JERE) is one of the most important tasks in information extraction. However, most existing works focus on sentence-level coarse-grained JERE, which have limitations in real-world scenarios. In this…

Document-level Relation Extraction (RE) requires extracting relations expressed within and across sentences. Recent works show that graph-based methods, usually constructing a document-level graph that captures document-aware interactions,…

Large language models with long context windows can answer complex questions directly from full-length academic, technical, and policy documents, but passing entire documents is often costly, slow, and can degrade answer quality while…

Social media enables data-driven analysis of public opinion on contested issues. Target-Stance Extraction (TSE) is the task of identifying the target discussed in a document and the document's stance towards that target. Many works classify…

Document-level relation extraction (DocRE) poses the challenge of identifying relationships between entities within a document as opposed to the traditional RE setting where a single sentence is input. Existing approaches rely on logical…

Tables are pervasive in diverse documents, making table recognition (TR) a fundamental task in document analysis. Existing modular TR pipelines separately model table structure and content, leading to suboptimal integration and complex…

Large Language Models (LLMs), while being increasingly dominant on a myriad of knowledge-intensive activities, have only had limited success understanding lengthy table-text mixtures, such as academic papers and financial reports. Recent…

Image-based table recognition is a challenging task due to the diversity of table styles and the complexity of table structures. Most of the previous methods focus on a non-end-to-end approach which divides the problem into two separate…

Document-level event extraction is a long-standing challenging information retrieval problem involving a sequence of sub-tasks: entity extraction, event type judgment, and event type-specific multi-event extraction. However, addressing the…

We focus on electronic theses and dissertations (ETDs), aiming to improve access and expand their utility, since more than 6 million are publicly available, and they constitute an important corpus to aid research and education across…