Related papers: Universal Information Extraction as Unified Semant…

Existing Image Manipulation Localization (IML) methods mostly rely heavily on task-specific designs, making them perform well only on the target IML task, while joint training on multiple IML tasks causes significant performance…

Overall, the two main contributions of this work include the application of sentence simplification to association extraction as described above, and the use of distributional semantics for concept extraction. The proposed work on concept…

The scaling of Large Language Models (LLMs) is increasingly limited by data quality. Most methods handle data mixing and sample selection separately, which can break the structure in code corpora. We introduce \textbf{UniGeM}, a framework…

Conventional Open Information Extraction (Open IE) systems are usually built on hand-crafted patterns from other NLP tools such as syntactic parsing, yet they face problems of error propagation. In this paper, we propose a neural Open IE…

Open Information Extraction (OIE) is a structured prediction (SP) task in Natural Language Processing (NLP) that aims to extract structured $n$-ary tuples - usually subject-relation-object triples - from free text. The word embeddings in…

Typically, information extraction (IE) requires a pipeline approach: first, a sequence labeling model is trained on manually annotated documents to extract relevant spans; then, when a new document arrives, a model predicts spans which are…

The multi-format information extraction task in the 2021 Language and Intelligence Challenge is designed to comprehensively evaluate information extraction from different dimensions. It consists of an multiple slots relation extraction…

Joint-event-extraction, which extracts structural information (i.e., entities or triggers of events) from unstructured real-world corpora, has attracted more and more research attention in natural language processing. Most existing works do…

While language tasks are naturally expressed in a single, unified, modeling framework, i.e., generating sequences of tokens, this has not been the case in computer vision. As a result, there is a proliferation of distinct architectures and…

This work establishes a rigorous theoretical foundation for analyzing deep learning systems by leveraging Infinite Time Turing Machines (ITTMs), which extend classical computation into transfinite ordinal steps. Using ITTMs, we reinterpret…

The discovery of new materials has a documented history of propelling human progress for centuries and more. The behaviour of a material is a function of its composition, structure, and properties, which further depend on its processing and…

Multimodal information extraction (MIE) constitutes a set of essential tasks aimed at extracting structural information from Web texts with integrating images, to facilitate the structural construction of Web-based semantic knowledge. To…

Knowledge understanding is a foundational part of envisioned 6G networks to advance network intelligence and AI-native network architectures. In this paradigm, information extraction plays a pivotal role in transforming fragmented telecom…

With rise of digital age, there is an explosion of information in the form of news, articles, social media, and so on. Much of this data lies in unstructured form and manually managing and effectively making use of it is tedious, boring and…

Unified multimodal models (UMMs) were designed to combine the reasoning ability of large language models (LLMs) with the generation capability of vision models. In practice, however, this synergy remains elusive: UMMs fail to transfer…

Information extraction (IE) for visually-rich documents (VRDs) has achieved SOTA performance recently thanks to the adaptation of Transformer-based language models, which shows the great potential of pre-training methods. In this paper, we…

Event extraction (EE) is an essential task of information extraction, which aims to extract structured event information from unstructured text. Most prior work focuses on extracting flat events while neglecting overlapped or nested ones. A…

Large language models (LLMs) are widely recognized for their exceptional capacity to capture semantics meaning. Yet, there remains no established metric to quantify this capability. In this work, we introduce a quantitative metric,…

Extracting entities and relations is an essential task of information extraction. Triplets extracted from a sentence might overlap with each other. Previous methods either did not address the overlapping issues or solved overlapping issues…

Decoding human brain activity from electroencephalography (EEG) signals is a central challenge at the intersection of neuroscience and artificial intelligence, enabling diverse applications in mental state assessment, clinical monitoring,…