Related papers: SRFUND: A Multi-Granularity Hierarchical Structure…

Table Structure Recognition (TSR) is vital for various downstream tasks like information retrieval, table reconstruction, and document understanding. While most state-of-the-art (SOTA) research predominantly focuses on TSR in English…

Automated document layout analysis remains a major challenge for low-resource, non-Latin scripts. Khmer is a language spoken daily by over 17 million people in Cambodia, receiving little attention in the development of document AI tools.…

Recent efforts of multimodal Transformers have improved Visually Rich Document Understanding (VrDU) tasks via incorporating visual and textual information. However, existing approaches mainly focus on fine-grained elements such as words and…

Thanks to information extraction and semantic Web efforts, search on unstructured text is increasingly refined using semantic annotations and structured knowledge bases. However, most users cannot become familiar with the schema of…

Constructing scientific multimodal document reasoning datasets for foundation model training involves an inherent trade-off among scale, faithfulness, and realism. To address this challenge, we introduce the synthesize-and-reground…

Extraction from raw text to a knowledge base of entities and fine-grained types is often cast as prediction into a flat set of entity and type labels, neglecting the rich hierarchies over types and entities contained in curated ontologies.…

This paper presents Structure Aware Dense Retrieval (SANTA) model, which encodes user queries and structured data in one universal embedding space for retrieving structured data. SANTA proposes two pretraining methods to make language…

Document chunking is a critical task in natural language processing (NLP) that involves dividing a document into meaningful segments. Traditional methods often rely solely on semantic analysis, ignoring the spatial layout of elements, which…

Extracting structured information from scientific literature is critical for accelerating discovery, yet Large Language Models (LLMs) often struggle in specialized domains that require expert knowledge and generalize poorly across tasks. We…

Prompt learning has become a prevalent strategy for adapting vision-language foundation models (VLMs) such as CLIP to downstream tasks. With the emergence of large language models (LLMs), recent studies have explored the potential of using…

The problem of document structure reconstruction refers to converting digital or scanned documents into corresponding semantic structures. Most existing works mainly focus on splitting the boundary of each element in a single document page,…

Collaborative dialogue relies on participants incrementally establishing common ground, yet in asymmetric settings they may believe they agree while referring to different entities. We introduce a perspectivist annotation scheme for the…

We propose a method to create document representations that reflect their internal structure. We modify Tree-LSTMs to hierarchically merge basic elements such as words and sentences into blocks of increasing complexity. Our Structure…

We introduce a novel task, called Generalized Relation Discovery (GRD), for open-world relation extraction. GRD aims to identify unlabeled instances in existing pre-defined relations or discover novel relations by assigning instances to…

NLP models that compare or consolidate information across multiple documents often struggle when challenged with recognizing substantial information redundancies across the texts. For example, in multi-document summarization it is crucial…

Producing outputs that satisfy both semantic intent and format constraints is essential for deploying large language models in user-facing and system-integrated workflows. In this work, we focus on Markdown formatting, which is ubiquitous…

Semi-structured knowledge bases (SKBs) embed textual documents in a typed graph of entities and relations, and underpin applications such as product search, academic paper search, and precision-medicine inquiries. Existing hybrid retrieval…

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…

Large pre-trained language models achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, they almost exclusively focus on text-only representation, while neglecting cell-level layout information that is important…

Text alignment finds application in tasks such as citation recommendation and plagiarism detection. Existing alignment methods operate at a single, predefined level and cannot learn to align texts at, for example, sentence and document…