Related papers: Universal Information Extraction as Unified Semant…

Unlike language tasks, where the output space is usually limited to a set of tokens, the output space of visual tasks is more complicated, making it difficult to build a unified visual model for various visual tasks. In this paper, we seek…

Zero-shot cross-lingual information extraction(IE) aims at constructing an IE model for some low-resource target languages, given annotations exclusively in some rich-resource languages. Recent studies based on language-universal features…

Decoding visual information from time-resolved brain recordings, such as EEG and MEG, plays a pivotal role in real-time brain-computer interfaces. However, existing approaches primarily focus on direct brain-image feature alignment and are…

A large-scale labeled dataset is a key factor for the success of supervised deep learning in computer vision. However, a limited number of annotated data is very common, especially in ophthalmic image analysis, since manual annotation is…

Information Extraction (IE) from the tables present in scientific articles is challenging due to complicated tabular representations and complex embedded text. This paper presents TabLeX, a large-scale benchmark dataset comprising table…

Event extraction is of practical utility in natural language processing. In the real world, it is a common phenomenon that multiple events existing in the same sentence, where extracting them are more difficult than extracting a single…

Information extraction from semi-structured documents is crucial for frictionless business-to-business (B2B) communication. While machine learning problems related to Document Information Extraction (IE) have been studied for decades, many…

Despite the progress of image segmentation for accurate visual entity segmentation, completing the diverse requirements of image editing applications for different-level region-of-interest selections remains unsolved. In this paper, we…

While there has been substantial progress in factoid question-answering (QA), answering complex questions remains challenging, typically requiring both a large body of knowledge and inference techniques. Open Information Extraction (Open…

Existing information retrieval (IR) models often assume a homogeneous format, limiting their applicability to diverse user needs, such as searching for images with text descriptions, searching for a news article with a headline image, or…

Recent years the task of incomplete utterance rewriting has raised a large attention. Previous works usually shape it as a machine translation task and employ sequence to sequence based architecture with copy mechanism. In this paper, we…

Automated resume information extraction is critical for scaling talent acquisition, yet its real-world deployment faces three major challenges: the extreme heterogeneity of resume layouts and content, the high cost and latency of large…

Recent advancements in large language models have shown impressive performance in general chat. However, their domain-specific capabilities, particularly in information extraction, have certain limitations. Extracting structured information…

In the last years, the consolidation of deep neural network architectures for information extraction in document images has brought big improvements in the performance of each of the tasks involved in this process, consisting of text…

In this work, we present SEEM, a promptable and interactive model for segmenting everything everywhere all at once in an image, as shown in Fig.1. In SEEM, we propose a novel decoding mechanism that enables diverse prompting for all types…

Many tasks in natural language processing require the extraction of relationship information for a given condition, such as event argument extraction, relation extraction, and task-oriented semantic parsing. Recent works usually propose…

Recently, visually-situated text parsing (VsTP) has experienced notable advancements, driven by the increasing demand for automated document understanding and the emergence of Generative Large Language Models (LLMs) capable of processing…

Visual Information Extraction (VIE) task aims to extract key information from multifarious document images (e.g., invoices and purchase receipts). Most previous methods treat the VIE task simply as a sequence labeling problem or…

Designing effective data manipulation methods is a long standing problem in data lakes. Traditional methods, which rely on rules or machine learning models, require extensive human efforts on training data collection and tuning models.…

Text indexing is a fundamental and well-studied problem. Classic solutions either replace the original text with a compressed representation, e.g., the FM-index and its variants, or keep it uncompressed but attach some redundancy - an index…