Related papers: TWIX: Automatically Reconstructing Structured Data…
HTML documents are an important medium for disseminating information on the Web for human consumption. An HTML document presents information in multiple text formats including unstructured text, structured key-value pairs, and tables.…
Re-finding electronic documents from a personal computer is a frequent demand to users. In a simple re-finding task, people can use many methods to retrieve a document, such as navigating directly to the document's folder, searching with a…
Traditionally a document is visualized by a word cloud. Recently, distributed representation methods for documents have been developed, which map a document to a set of topic embeddings. Visualizing such a representation is useful to…
Tables are a primary medium for conveying critical information in administrative domains, yet their complexity hinders utilization by Large Language Models (LLMs). This paper introduces the Theme-Explanation Structure-based Table…
Web usage mining is a process of extracting useful information from server logs i.e. users history. Web usage mining is a process of finding out what users are looking for on the internet. Some users might be looking at only textual data,…
Large, pre-trained transformer models like BERT have achieved state-of-the-art results on document understanding tasks, but most implementations can only consider 512 tokens at a time. For many real-world applications, documents can be much…
Two-dimensional data maps can visually reveal information about the relations between data instances. Popular techniques to construct data maps are t-SNE and UMAP. The resulting point-based visualizations, though, provide information only…
Vision-Language Models (VLMs) have made remarkable progress in document-based Visual Question Answering (i.e., responding to queries about the contents of an input document provided as an image). In this work, we show these models can…
Transforming unstructured text into structured data is a complex task, requiring semantic understanding, reasoning, and structural comprehension. While Large Language Models (LLMs) offer potential, they often struggle with handling…
Search engines have become an indispensable tool for browsing information on the Internet. The user, however, is often annoyed by redundant results from irrelevant Web pages. One reason is because search engines also look at non-informative…
Recently, significant progress has been made applying machine learning to the problem of table structure inference and extraction from unstructured documents. However, one of the greatest challenges remains the creation of datasets with…
Large Language Models (LLMs) demonstrate remarkable capabilities in replicating human tasks and boosting productivity. However, their direct application for data extraction presents limitations due to a prioritisation of fluency over…
Over the past few decades, the amount of scientific articles and technical literature has increased exponentially in size. Consequently, there is a great need for systems that can ingest these documents at scale and make their content…
The proliferation of multimodal Large Language Models has significantly advanced the ability to analyze and understand complex data inputs from different modalities. However, the processing of long documents remains under-explored, largely…
Data curation is commonly considered a "secret-sauce" for LLM training, with higher quality data usually leading to better LLM performance. Given the scale of internet-scraped corpora, data pruning has become a larger and larger focus.…
Large Language Models (LLMs) have demonstrated strong capabilities in transforming text descriptions or tables to data visualizations via instruction-tuning methods. However, it is not straightforward to apply these methods directly for a…
Semi-structured content in HTML tables, lists, and infoboxes accounts for a substantial share of factual data on the web, yet the formatting complicates usage, and reliably extracting structured information from them remains challenging.…
Key information extraction from document images is of paramount importance in office automation. Conventional template matching based approaches fail to generalize well to document images of unseen templates, and are not robust against text…
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…
Semi-structured and unstructured data management is challenging, but many of the problems encountered are analogous to problems already addressed in the relational context. In the area of information extraction, for example, the shift from…