Abstract Information Extraction (IE) from document images is challenging due to the high
variability of layout formats. Deep models such as etc. In this work, we propose a novel …

In recent years, natural language processing has gained significant popularity in various
sectors, including the legal domain. This paper presents NeCo Team's solutions to the …

Background: In the information extraction and natural language processing domain,
accessible datasets are crucial to reproduce and compare results. Publicly available …

State-of-the-art solutions for Natural Language Processing (NLP) are able to capture a
broad range of contexts, like the sentence-level context or document-level context for short …

Most state-of-the-art information extraction approaches rely on token-level labels to find the
areas of interest in text. Unfortunately, these labels are time-consuming and costly to create …

Many business workflows require extracting important fields from form-like documents (eg
bank statements, bills of lading, purchase orders, etc.). Recent techniques for automating …

Extracting structured data from HTML documents is a long-studied problem with a broad
range of applications like augmenting knowledge bases, supporting faceted search, and …

Recent end-to-end encoder-decoder neural models for data-to-text generation can produce
fluent and seemingly informative texts despite these models disregard the traditional content …

As an essential task for the architecture, engineering, and construction (AEC) industry,
information retrieval (IR) from unstructured textual data based on natural language …

End-to-end question answering (QA) requires both information retrieval (IR) over a large
document collection and machine reading comprehension (MRC) on the retrieved …