Related papers: DOM-LM: Learning Generalizable Representations for…
Large Language Model (LLM) pre-training exhausts an ever growing compute budget, yet recent research has demonstrated that careful document selection enables comparable model quality with only a fraction of the FLOPs. Inspired by efforts…
Representation learning on text-attributed graphs (TAGs) has become a critical research problem in recent years. A typical example of a TAG is a paper citation graph, where the text of each paper serves as node attributes. Initial graph…
Graphs provide a unified representation of semantic content and relational structure, making them a natural fit for domains such as molecular modeling, citation networks, and social graphs. Meanwhile, large language models (LLMs) have…
We propose a method to create document representations that reflect their internal structure. We modify Tree-LSTMs to hierarchically merge basic elements such as words and sentences into blocks of increasing complexity. Our Structure…
This thesis tackles the problem of learning efficient representations of complex, structured data with a natural application to web page and element classification. We hypothesise that the context around the element inside the web page is…
Relational understanding is critical for a number of visually-rich documents (VRDs) understanding tasks. Through multi-modal pre-training, recent studies provide comprehensive contextual representations and exploit them as prior knowledge…
Hierarchical neural architectures are often used to capture long-distance dependencies and have been applied to many document-level tasks such as summarization, document segmentation, and sentiment analysis. However, effective usage of such…
Recent document question answering models consist of two key components: the vision encoder, which captures layout and visual elements in images, and a Large Language Model (LLM) that helps contextualize questions to the image and…
We suggest to employ techniques from Natural Language Processing (NLP) and Knowledge Representation (KR) to transform existing documents into documents amenable for the Semantic Web. Semantic Web documents have at least part of their…
Interacting with the legal system and the government requires the assembly and analysis of various pieces of information that can be spread across different (paper) documents, such as forms, certificates and contracts (e.g. leases). This…
Most of the existing medication recommendation models are predicted with only structured data such as medical codes, with the remaining other large amount of unstructured or semi-structured data underutilization. To increase the utilization…
Text-rich document understanding (TDU) requires comprehensive analysis of documents containing substantial textual content and complex layouts. While Multimodal Large Language Models (MLLMs) have achieved fast progress in this domain,…
Automatically generating a presentation from the text of a long document is a challenging and useful problem. In contrast to a flat summary, a presentation needs to have a better and non-linear narrative, i.e., the content of a slide can…
Visual document understanding (VDU) is a challenging task that involves understanding documents across various modalities (text and image) and layouts (forms, tables, etc.). This study aims to enhance generalizability of small VDU models by…
Understanding and extracting of information from large documents, such as business opportunities, academic articles, medical documents and technical reports, poses challenges not present in short documents. Such large documents may be…
Document layout understanding is a field of study that analyzes the spatial arrangement of information in a document hoping to understand its structure and layout. Models such as LayoutLM (and its subsequent iterations) can understand…
Recent advances in training large language models (LLMs) using massive amounts of solely textual data lead to strong generalization across many domains and tasks, including document-specific tasks. Opposed to that there is a trend to train…
Text structuralization is one of the important fields of natural language processing (NLP) consists of information extraction (IE) and structure formalization. However, current studies of text structuralization suffer from a shortage of…
In recent years, efforts have been made to use text information for better user profiling and item characterization in recommendations. However, text information can sometimes be of low quality, hindering its effectiveness for real-world…
With recent advancements in Large Language Models (LLMs) and growing interest in retrieval-augmented generation (RAG), the ability to understand table structures has become increasingly important. This is especially critical in financial…