Related papers: Sheet as Token: A Graph-Enhanced Representation fo…

In recent years, simultaneous learning of multiple dense prediction tasks with partially annotated label data has emerged as an important research area. Previous works primarily focus on leveraging cross-task relations or conducting…

How can we best encode structured data into sequential form for use in large language models (LLMs)? In this work, we introduce a parameter-efficient method to explicitly represent structured data for LLMs. Our method, GraphToken, learns an…

Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to…

With the widespread use of mobile phones and scanners to photograph and upload documents, the need for extracting the information trapped in unstructured document images such as retail receipts, insurance claim forms and financial invoices…

One of the most important assets of any company is being able to easily access information on itself and on its business. In this line, it has been observed that this important information is often stored in one of the millions of…

Span-based joint extraction simultaneously conducts named entity recognition (NER) and relation extraction (RE) in text span form. Recent studies have shown that token labels can convey crucial task-specific information and enrich token…

A central challenge in science is to understand how systems behaviors emerge from complex networks. This often requires aggregating, reusing, and integrating heterogeneous information. Supplementary spreadsheets to articles are a key data…

Document-level relation extraction aims to extract relations among multiple entity pairs from a document. Previously proposed graph-based or transformer-based models utilize the entities independently, regardless of global information among…

Efficiently identifying keyphrases that represent a given document is a challenging task. In the last years, plethora of keyword detection approaches were proposed. These approaches can be based on statistical (frequency-based) properties…

Graph-based convolutional model such as non-local block has shown to be effective for strengthening the context modeling ability in convolutional neural networks (CNNs). However, its pixel-wise computational overhead is prohibitive which…

Legacy spreadsheets are both, an asset, and an enduring problem concerning spreadsheets in business. To make spreadsheets stay alive and remain correct, comprehension of a given spreadsheet is highly important. Visualization techniques…

A mind-map is a diagram that represents the central concept and key ideas in a hierarchical way. Converting plain text into a mind-map will reveal its key semantic structure and be easier to understand. Given a document, the existing…

Large language models have evolved to process multiple modalities beyond text, such as images and audio, which motivates us to explore how to effectively leverage them for graph reasoning tasks. The key question, therefore, is how to…

Graph-based semi-supervised learning has proven to be an effective approach for query-focused multi-document summarization. The problem of previous semi-supervised learning is that sentences are ranked without considering the higher level…

Representing structured text from complex documents typically calls for different machine learning techniques, such as language models for paragraphs and convolutional neural networks (CNNs) for table extraction, which prohibits drawing…

This paper presents a toolkit for spreadsheet visualization based on logical areas, semantic classes and data modules. Logical areas, semantic classes and data modules are abstract representations of spreadsheet programs that are meant to…

Event extraction, the technology that aims to automatically get the structural information from documents, has attracted more and more attention in many fields. Most existing works discuss this issue with the token-level multi-label…

Learning the right graph representation from noisy, multisource data has garnered significant interest in recent years. A central tenet of this problem is relational learning. Here the objective is to incorporate the partial information…

Tables have been an ever-existing structure to store data. There exist now different approaches to store tabular data physically. PDFs, images, spreadsheets, and CSVs are leading examples. Being able to parse table structures and extract…

Table Detection has become a fundamental task for visually rich document understanding with the surging number of electronic documents. However, popular public datasets widely used in related studies have inherent limitations, including…