Related papers: Domain Knowledge Empowered Structured Neural Net f…

Structured neuron encapsulation introduces a modular framework that enables more effective aggregation and specialization of information within deep learning architectures. A model modified through this framework demonstrated improved…

Distant Supervised Relation Extraction (DSRE) is usually formulated as a problem of classifying a bag of sentences that contain two query entities, into the predefined relation classes. Most existing methods consider those relation classes…

In recent years, there has been an increasing number of frameworks developed for biomedical entity and relation extraction. This research effort aims to address the accelerating growth in biomedical publications and the intricate nature of…

While deep neural networks have achieved impressive performance on a range of NLP tasks, these data-hungry models heavily rely on labeled data, which restricts their applications in scenarios where data annotation is expensive. Natural…

The principle of optimism in the face of uncertainty underpins many theoretically successful reinforcement learning algorithms. In this paper we provide a general framework for designing, analyzing and implementing such algorithms in the…

Deep Learning models have become dominant in tackling financial time-series analysis problems, overturning conventional machine learning and statistical methods. Most often, a model trained for one market or security cannot be directly…

The broad set of deep generative models (DGMs) has achieved remarkable advances. However, it is often difficult to incorporate rich structured domain knowledge with the end-to-end DGMs. Posterior regularization (PR) offers a principled…

Lagrangian decomposition (LD) is a relaxation method that provides a dual bound for constrained optimization problems by decomposing them into more manageable sub-problems. This bound can be used in branch-and-bound algorithms to prune the…

Deep neural networks for visual perception are highly susceptible to domain shift, which poses a critical challenge for real-world deployment under conditions that differ from the training data. To address this domain generalization…

Retrieval-Augmented Generation (RAG) improves large language models by retrieving external knowledge, often truncated into smaller chunks due to the input context window, which leads to information loss, resulting in response hallucinations…

Named entity recognition often fails in idiosyncratic domains. That causes a problem for depending tasks, such as entity linking and relation extraction. We propose a generic and robust approach for high-recall named entity recognition. Our…

Accurate long series forecasting of traffic information is critical for the development of intelligent traffic systems. We may benefit from the rapid growth of neural network analysis technology to better understand the underlying…

Modern high-stakes systems, such as healthcare or robotics, often generate vast streaming event sequences. Our goal is to design an efficient, plug-and-play tool to elicit logic tree-based explanations from Large Language Models (LLMs) to…

Dynamic recommendation systems aim to provide personalized suggestions by modeling temporal user-item interactions across time-series behavioral data. Recent studies have leveraged pre-trained dynamic graph neural networks (GNNs) to learn…

Forecasting time series with extreme events has been a challenging and prevalent research topic, especially when the time series data are affected by complicated uncertain factors, such as is the case in hydrologic prediction. Diverse…

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter difficulties related to dimensionality and limited…

Query performance prediction, the task of predicting the latency of a query, is one of the most challenging problem in database management systems. Existing approaches rely on features and performance models engineered by human experts, but…

Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. However, they are often overconfident in their predictions, which leads to inaccurate and miscalibrated…

Extracting relations from text corpora is an important task in text mining. It becomes particularly challenging when focusing on weakly-supervised relation extraction, that is, utilizing a few relation instances (i.e., a pair of entities…

Causal knowledge extraction is the task of extracting relevant causes and effects from text by detecting the causal relation. Although this task is important for language understanding and knowledge discovery, recent works in this domain…