Related papers: MoDora: Tree-Based Semi-Structured Document Analys…
State-of-the-art offline Optical Character Recognition (OCR) frameworks perform poorly on semi-structured handwritten domain-specific documents due to their inability to localize and label form fields with domain-specific semantics.…
In long, multi-page industrial documents, retrieval-augmented generation (RAG) depends heavily on whether chunk boundaries follow the document's true structure. Existing text-centric chunkers and generative hierarchy parsers often miss…
The traditional RAG paradigm, which typically engages in the comprehension of relevant text chunks in response to received queries, inherently restricts both the depth of knowledge internalization and reasoning capabilities. To address this…
Person-job fit is an essential part of online recruitment platforms in serving various downstream applications like Job Search and Candidate Recommendation. Recently, pretrained large language models have further enhanced the effectiveness…
We introduce MonkeyOCR, a document parsing model that advances the state of the art by leveraging a Structure-Recognition-Relation (SRR) triplet paradigm. This design simplifies what would otherwise be a complex multi-tool pipeline and…
Document understanding is critical for applications from financial analysis to scientific discovery. Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs), face key…
Retrieval-augmented generation over semi-structured sources such as HTML is constrained by a mismatch between document structure and the flat, sequence-based interfaces of today's embedding and generative models. Retrieval pipelines often…
Legal judgment prediction suffers from the problem of long case documents exceeding tens of thousands of words, in general, and having a non-uniform structure. Predicting judgments from such documents becomes a challenging task, more so on…
The ubiquity and value of tables as semi-structured data across various domains necessitate advanced methods for understanding their complexity and vast amounts of information. Despite the impressive capabilities of large language models…
Tables are information-rich structured objects in document images. While significant work has been done in localizing tables as graphic objects in document images, only limited attempts exist on table structure recognition. Most existing…
Document parsing is a core task in document intelligence, supporting applications such as information extraction, retrieval-augmented generation, and automated document analysis. However, real-world documents often feature complex layouts…
Current approaches to machine translation (MT) either translate sentences in isolation, disregarding the context they appear in, or model context at the level of the full document, without a notion of any internal structure the document may…
Document layout analysis is a known problem to the documents research community and has been vastly explored yielding a multitude of solutions ranging from text mining, and recognition to graph-based representation, visual feature…
Large language models record impressive performance on many natural language processing tasks. However, their knowledge capacity is limited to the pretraining corpus. Retrieval augmentation offers an effective solution by retrieving context…
Structured text understanding on Visually Rich Documents (VRDs) is a crucial part of Document Intelligence. Due to the complexity of content and layout in VRDs, structured text understanding has been a challenging task. Most existing…
Nowadays, data are generated massively and rapidly from scientific fields as bioinformatics, neuroscience and astronomy to business and engineering fields. Cluster analysis, as one of the major data analysis tools, is therefore more…
Large Language Models (LLMs) exhibit a well-documented positional bias when processing long input contexts: information in the middle of a context window receives substantially less attention than content at the boundaries, a phenomenon…
We address the extraction of mathematical statements and their proofs from scholarly PDF articles as a multimodal classification problem, utilizing text, font features, and bitmap image renderings of PDFs as distinct modalities. We propose…
In recent years, the use of multi-modal pre-trained Transformers has led to significant advancements in visually-rich document understanding. However, existing models have mainly focused on features such as text and vision while neglecting…
Automatic legal judgment prediction and its explanation suffer from the problem of long case documents exceeding tens of thousands of words, in general, and having a non-uniform structure. Predicting judgments from such documents and…