English
Related papers

Related papers: MoDora: Tree-Based Semi-Structured Document Analys…

200 papers

We study the problem of weakly supervised text classification, which aims to classify text documents into a set of pre-defined categories with category surface names only and without any annotated training document provided. Most existing…

Computation and Language · Computer Science 2023-10-24 Yu Zhang , Shweta Garg , Yu Meng , Xiusi Chen , Jiawei Han

Ontologies provide features like a common vocabulary, reusability, machine-readable content, and also allows for semantic search, facilitate agent interaction and ordering & structuring of knowledge for the Semantic Web (Web 3.0)…

Information Retrieval · Computer Science 2017-09-08 Monika Rani , Amit Kumar Dhar , O. P. Vyas

Advances in Visually Rich Document Understanding (VrDU) have enabled information extraction and question answering over documents with complex layouts. Two tropes of architectures have emerged -- transformer-based models inspired by LLMs,…

Computation and Language · Computer Science 2024-01-08 Dongsheng Wang , Zhiqiang Ma , Armineh Nourbakhsh , Kang Gu , Sameena Shah

Large Language Models (LLMs) often produce monolithic text that is hard to edit in parts, which can slow down collaborative workflows. We present componentization, an approach that decomposes model outputs into modular, independently…

Human-Computer Interaction · Computer Science 2025-09-11 Ryan Lingo , Rajeev Chhajer , Martin Arroyo , Luka Brkljacic , Ben Davis , Nithin Santhanam

Large Language Models (LLMs) have achieved remarkable success across a wide spectrum of natural language processing tasks. However, their ever-growing scale introduces significant barriers to real-world deployment, including substantial…

Computation and Language · Computer Science 2026-01-07 Guangxin Wu , Hao Zhang , Zhang Zhibin , Jiafeng Guo , Xueqi Cheng

We present a novel method for hierarchical topic detection where topics are obtained by clustering documents in multiple ways. Specifically, we model document collections using a class of graphical models called hierarchical latent tree…

Computation and Language · Computer Science 2016-12-22 Peixian Chen , Nevin L. Zhang , Tengfei Liu , Leonard K. M. Poon , Zhourong Chen , Farhan Khawar

How to efficiently generate an accurate, well-structured overview report (ORPT) over thousands of related documents is challenging. A well-structured ORPT consists of sections of multiple levels (e.g., sections and subsections). None of the…

Computation and Language · Computer Science 2019-08-20 Jingwen Wang , Hao Zhang , Cheng Zhang , Wenjing Yang , Liqun Shao , Jie Wang

Retrieval-augmented generation (RAG) enhances large language models with external knowledge, and tree-based RAG organizes documents into hierarchical indexes to support queries at multiple granularities. However, existing Tree-RAG methods…

Machine Learning · Computer Science 2026-05-04 Ziwen Zhao , Menglin Yang

Chemical structure extraction from documents remains a hard problem due to both false positive identification of structures during segmentation and errors in the predicted structures. Current approaches rely on handcrafted rules and…

Machine Learning · Computer Science 2018-02-15 Joshua Staker , Kyle Marshall , Robert Abel , Carolyn McQuaw

Real-world document question answering is challenging. Analysts must synthesize evidence across multiple documents and different parts of each document. However, any fixed LLM context window can be exceeded as document collections grow. A…

Computation and Language · Computer Science 2026-04-27 Harshit Joshi , Priyank Shethia , Jadelynn Dao , Monica S. Lam

In the last years' digitalization process, the creation and management of documents in various domains, particularly in Public Administration (PA), have become increasingly complex and diverse. This complexity arises from the need to handle…

Computation and Language · Computer Science 2024-02-26 Emanuele Musumeci , Michele Brienza , Vincenzo Suriani , Daniele Nardi , Domenico Daniele Bloisi

Cross-lingual cross-modal retrieval (CCR) aims to retrieve visually relevant content based on non-English queries, without relying on human-labeled cross-modal data pairs during training. One popular approach involves utilizing machine…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Yabing Wang , Le Wang , Qiang Zhou , Zhibin Wang , Hao Li , Gang Hua , Wei Tang

This paper presents a method for the automated collection and aggregation of unstructured data from diverse web sources, utilizing Large Language Models (LLMs). The primary challenge with existing techniques is their instability when the…

Databases · Computer Science 2026-04-21 Vsevolod Lazebnyi , Natalia Tereshkina , Maria Shabarina , Dmitriy Fedorov

User queries in real-world recommendation systems often combine structured constraints (e.g., category, attributes) with unstructured preferences (e.g., product descriptions or reviews). We introduce HyST (Hybrid retrieval over…

Information Retrieval · Computer Science 2025-08-26 Jiyoon Myung , Jihyeon Park , Joohyung Han

The rapid evolution of intelligent document processing systems demands robust solutions that adapt to diverse domains without extensive retraining. Traditional methods often falter with variable document types, leading to poor performance.…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Maria Pilligua , Nil Biescas , Javier Vazquez-Corral , Josep Lladós , Ernest Valveny , Sanket Biswas

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…

Computation and Language · Computer Science 2025-01-13 Prashant Verma

Automatic coding of International Classification of Diseases (ICD) is a multi-label text categorization task that involves extracting disease or procedure codes from clinical notes. Despite the application of state-of-the-art natural…

Machine Learning · Computer Science 2023-10-17 Chang Lu , Chandan K. Reddy , Ping Wang , Yue Ning

In semi-supervised segmentation, capturing meaningful semantic structures from unlabeled data is essential. This is particularly challenging in histopathology image analysis, where objects are densely distributed. To address this issue, we…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Meilong Xu , Xiaoling Hu , Shahira Abousamra , Chen Li , Chao Chen

Retrieval-augmented generation (RAG) systems that answer questions from document collections face compounding difficulties when high-precision citations are required: flat chunking strategies sacrifice document structure, single-query…

Computation and Language · Computer Science 2026-03-10 Shih-Ying Yeh , Yueh-Feng Ku , Ko-Wei Huang , Buu-Khang Tu

Document retrieval is one of the most challenging tasks in Information Retrieval. It requires handling longer contexts, often resulting in higher query latency and increased computational overhead. Recently, Learned Sparse Retrieval (LSR)…

Information Retrieval · Computer Science 2025-04-09 Emmanouil Georgios Lionis , Jia-Huei Ju