Related papers: TreeForm: End-to-end Annotation and Evaluation for…

Many business documents processed in modern NLP and IR pipelines are visually rich: in addition to text, their semantics can also be captured by visual traits such as layout, format, and fonts. We study the problem of information extraction…

We propose a new optimization-based approach for feature selection in tree ensembles, an important problem in statistics and machine learning. Popular tree ensemble toolkits e.g., Gradient Boosted Trees and Random Forests support feature…

Semantic segmentation based on sparse annotation has advanced in recent years. It labels only part of each object in the image, leaving the remainder unlabeled. Most of the existing approaches are time-consuming and often necessitate a…

For text summarization, the role of discourse structure is pivotal in discerning the core content of a text. Regrettably, prior studies on incorporating Rhetorical Structure Theory (RST) into transformer-based summarization models only…

Automating information extraction from form-like documents at scale is a pressing need due to its potential impact on automating business workflows across many industries like financial services, insurance, and healthcare. The key challenge…

Program comprehension is a fundamental task in software development and maintenance processes. Software developers often need to understand a large amount of existing code before they can develop new features or fix bugs in existing…

Visually Rich Documents (VRDs) play a vital role in domains such as academia, finance, healthcare, and marketing, as they convey information through a combination of text, layout, and visual elements. Traditional approaches to extracting…

In this work we define a novel edit distance for trees considered with some abstract weights on the edges. The metric is driven by the idea of considering trees as topological summaries in the context of persistence and topological data…

We present our contribution to the IWPT 2021 shared task on parsing into enhanced Universal Dependencies. Our main system component is a hybrid tree-graph parser that integrates (a) predictions of spanning trees for the enhanced graphs with…

Key Information Extraction (KIE) is aimed at extracting structured information (e.g. key-value pairs) from form-style documents (e.g. invoices), which makes an important step towards intelligent document understanding. Previous approaches…

Accurate estimation of plant skeletal structure (e.g., branching structure) from images is essential for smart agriculture and plant science. Unlike human skeletons with fixed topology, plant skeleton estimation presents a unique challenge,…

Learning sophisticated feature interactions behind user behaviors is critical in maximizing CTR for recommender systems. Despite great progress, existing methods have a strong bias towards low- or high-order interactions, or rely on…

Autonomous navigation in unstructured vegetated environments remains an open challenge. To successfully operate in these settings, ground vehicles must assess the traversability of the environment and determine which vegetation is pliable…

While many NLP pipelines assume raw, clean texts, many texts we encounter in the wild, including a vast majority of legal documents, are not so clean, with many of them being visually structured documents (VSDs) such as PDFs. Conventional…

Recently, two-stage fine-tuning strategies, e.g., acquiring essential driving knowledge through supervised fine-tuning (SFT) and further enhancing decision-making and planning via reinforcement fine-tuning (RFT), have shown strong potential…

This paper proposes a medical text summarization method based on LongFormer, aimed at addressing the challenges faced by existing models when processing long medical texts. Traditional summarization methods are often limited by short-term…

Reading comprehension models are based on recurrent neural networks that sequentially process the document tokens. As interest turns to answering more complex questions over longer documents, sequential reading of large portions of text…

The latest developments in Natural Language Processing (NLP) have demonstrated remarkable progress in a code-text retrieval problem. As the Transformer-based models used in this task continue to increase in size, the computational costs and…

The French TreeBank developed at the University Paris 7 is the main source of morphosyntactic and syntactic annotations for French. However, it does not include explicit information related to named entities, which are among the most useful…

Image segmentation is a fundamental problem in biomedical image analysis. Recent advances in deep learning have achieved promising results on many biomedical image segmentation benchmarks. However, due to large variations in biomedical…