English
Related papers

Related papers: From Surface to Semantics: Semantic Structure Pars…

200 papers

We present an end-to-end, multimodal, fully convolutional network for extracting semantic structures from document images. We consider document semantic structure extraction as a pixel-wise segmentation task, and propose a unified model…

Computer Vision and Pattern Recognition · Computer Science 2017-06-09 Xiao Yang , Ersin Yumer , Paul Asente , Mike Kraley , Daniel Kifer , C. Lee Giles

Semantic parsing aims to map natural language utterances onto machine interpretable meaning representations, aka programs whose execution against a real-world environment produces a denotation. Weakly-supervised semantic parsers are trained…

Computation and Language · Computer Science 2019-09-11 Bailin Wang , Ivan Titov , Mirella Lapata

Data workers usually seek to understand the semantics of data wrangling scripts in various scenarios, such as code debugging, reusing, and maintaining. However, the understanding is challenging for novice data workers due to the variety of…

Software Engineering · Computer Science 2022-09-29 Kai Xiong , Zhongsu Luo , Siwei Fu , Yongheng Wang , Mingliang Xu , Yingcai Wu

In the era of large language models, Text-to-SQL, as a natural language interface for databases, is playing an increasingly important role. The sota Text-to-SQL models have achieved impressive accuracy, but their performance critically…

Databases · Computer Science 2026-02-13 Yafeng Nan , Haifeng Sun , Zirui Zhuang , Qi Qi , Guojun Chu , Jianxin Liao , Dan Pei , Jingyu Wang

Recent large language models (LLMs) have advanced table understanding capabilities but rely on converting tables into text sequences. While multimodal large language models (MLLMs) enable direct visual processing, they face limitations in…

Computation and Language · Computer Science 2025-02-26 Bohao Yang , Yingji Zhang , Dong Liu , André Freitas , Chenghua Lin

Page-level analysis of documents has been a topic of interest in digitization efforts, and multimodal approaches have been applied to both classification and page stream segmentation. In this work, we focus on capturing finer semantic…

Machine Learning · Computer Science 2022-05-27 Mehmet Arif Demirtaş , Berke Oral , Mehmet Yasin Akpınar , Onur Deniz

In this paper, we propose Agentar-Fin-OCR, a document parsing system tailored to financial-domain documents, transforming ultra-long financial PDFs into semantically consistent, highly accurate, structured outputs with auditing-grade…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Siyi Qian , Xiongfei Bai , Bingtao Fu , Yichen Lu , Gaoyang Zhang , Xudong Yang , Peng Zhang

Non-textual components such as charts, diagrams and tables provide key information in many scientific documents, but the lack of large labeled datasets has impeded the development of data-driven methods for scientific figure extraction. In…

Digital Libraries · Computer Science 2018-06-01 Noah Siegel , Nicholas Lourie , Russell Power , Waleed Ammar

Query-focused summarization over multi-table data is a challenging yet critical task for extracting precise and relevant information from structured data. Existing methods often rely on complex preprocessing steps and struggle to generalize…

Computation and Language · Computer Science 2024-12-13 Xiaochuan Lin , Xiangyong Chen

Efficient and accurate extraction of key information from 2D engineering drawings is essential for advancing digital manufacturing workflows. Such information includes geometric dimensioning and tolerancing (GD&T), measures, material…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Muhammad Tayyab Khan , Lequn Chen , Zane Yong , Jun Ming Tan , Wenhe Feng , Seung Ki Moon

Important information that relates to a specific topic in a document is often organized in tabular format to assist readers with information retrieval and comparison, which may be difficult to provide in natural language. However, tabular…

Computer Vision and Pattern Recognition · Computer Science 2020-03-05 Xu Zhong , Elaheh ShafieiBavani , Antonio Jimeno Yepes

Form understanding depends on both textual contents and organizational structure. Although modern OCR performs well, it is still challenging to realize general form understanding because forms are commonly used and of various formats. The…

Computer Vision and Pattern Recognition · Computer Science 2020-10-23 Zilong Wang , Mingjie Zhan , Xuebo Liu , Ding Liang

Semantic parsing is the task of translating natural language utterances into machine-readable meaning representations. Currently, most semantic parsing methods are not able to utilize contextual information (e.g. dialogue and comments…

Computation and Language · Computer Science 2020-11-03 Zhuang Li , Lizhen Qu , Gholamreza Haffari

Unstructured data formats account for over 80% of the data currently stored, and extracting value from such formats remains a considerable challenge. In particular, current approaches for managing unstructured documents do not support…

Web is a wide term which mainly consists of surface web and hidden web. One can easily access the surface web using traditional web crawlers, but they are not able to crawl the hidden portion of the web. These traditional crawlers retrieve…

Information Retrieval · Computer Science 2015-09-24 Manvi , Komal Kumar Bhatia , Ashutosh Dixit

Processing structured tabular data, particularly large and lengthy tables, constitutes a fundamental yet challenging task for large language models (LLMs). However, existing long-context benchmarks like Needle-in-a-Haystack primarily focus…

Computation and Language · Computer Science 2025-10-29 Lanrui Wang , Mingyu Zheng , Hongyin Tang , Zheng Lin , Yanan Cao , Jingang Wang , Xunliang Cai , Weiping Wang

Due to the large volume of data and information generated by a multitude of social data sources, it is a huge challenge to manage and extract useful knowledge, especially given the different forms of data, streaming data and uncertainty and…

Databases · Computer Science 2021-05-10 Bilal Abu-Salih , Pornpit Wongthongtham , Dengya Zhu , Kit Yan Chan , Amit Rudra

We propose a novel framework for summarizing structured enterprise data across multiple dimensions using large language model (LLM)-based agents. Traditional table-to-text models often lack the capacity to reason across hierarchical…

Artificial Intelligence · Computer Science 2025-08-12 Amit Dhanda

Tabular data provide answers to a significant portion of search queries. However, reciting an entire result table is impractical in conversational search systems. We propose to generate natural language summaries as answers to describe the…

Information Retrieval · Computer Science 2020-07-13 Shuo Zhang , Zhuyun Dai , Krisztian Balog , Jamie Callan

The generation of precise and detailed Table-Of-Contents (TOC) from a document is a problem of major importance for document understanding and information extraction. Despite its importance, it is still a challenging task, especially for…

Computation and Language · Computer Science 2019-11-21 Najah-Imane Bentabet , Rémi Juge , Sira Ferradans