However, most existing KGE works focus on the design of delicate triple modeling function, which mainly tell us how to measure the plausibility of observed triples, but we have limited understanding of why the methods can extrapolate to unseen data, and what are the important factors to help KGE extrapolate.
It ignores meaningful associations among event types and argument roles, leading to relatively poor performance for less frequent types/roles.
Finally, the content feature is normalized so that they demonstrate the same local feature statistics as the calculated per-point weighted style feature statistics.
Numerous methods, datasets, and evaluation metrics have been proposed in the literature, raising the need for a comprehensive and updated survey.
Event extraction (EE) is a crucial information extraction task that aims to extract event information in texts.
Our approach leverages knowledge of the already extracted arguments of the same sentence to determine the role of arguments that would be difficult to decide individually.
Sinkhorn divergence has become a very popular metric to compare probability distributions in optimal transport.
1 code implementation • 31 May 2021 • Yang Deng, Ce Wang, Yuan Hui, Qian Li, Jun Li, Shiwei Luo, Mengke Sun, Quan Quan, Shuxin Yang, You Hao, Pengbo Liu, Honghu Xiao, Chunpeng Zhao, Xinbao Wu, S. Kevin Zhou
Spine-related diseases have high morbidity and cause a huge burden of social cost.
In our study, we advance the causal inference research by proposing a new effective framework to estimate the treatment effect on stochastic intervention.
A common practice to address MNAR is to treat missing entries from the so-called "exposure" perspective, i. e., modeling how an item is exposed (provided) to a user.
A low complexity frequency offset estimation algorithm based on all-phase FFT for M-QAM is proposed.
Counterfactual explanation is one branch of interpretable machine learning that produces a perturbation sample to change the model's original decision.
We evaluate QA2MN on PathQuestion and WorldCup2014, two representative datasets for complex multi-hop question answering.
Our solution is based on the observation that continual learning of a task sequence inevitably interferes few-shot generalization, which makes it highly nontrivial to extend few-shot learning strategies to continual learning scenarios.
Learning and analyzing rap lyrics is a significant basis for many web applications, such as music recommendation, automatic music categorization, and music information retrieval, due to the abundant source of digital music in the World Wide Web.
More importantly, we show that using such a sinogram extrapolation module significantly improves the generalization capability of the model on unseen datasets (e. g., COVID-19 and LIDC datasets) when compared to existing approaches.
Ours is suitable for large-scale datasets, and experimental results show that our method is 82% faster than the violent retrieval for the single-frame detection.
Our study investigates the spammer detection problem in the context of multi-relation social networks, and makes an attempt to fully exploit the sequences of heterogeneous relations for enhancing the detection accuracy.
The last decade has seen a surge of research in this area due to the unprecedented success of deep learning.
Therefore, based on semantic features, we propose a Top-C classification loss (i. e., TCL-C) for classification task and a category-based grouping mechanism for category-based meta-features obtained by the meta-model.
Skin conditions are reported the 4th leading cause of nonfatal disease burden worldwide.
Recent years have witnessed the rapid growth of machine learning in a wide range of fields such as image recognition, text classification, credit scoring prediction, recommendation system, etc.
SBA stochastically decides whether to augment at iterations controlled by the batch scheduler and in which a ''distilled'' dynamic soft label regularization is introduced by incorporating the similarity in the vicinity distribution respect to raw samples.
The COVID-19 is sweeping the world with deadly consequences.
no code implementations • 7 Apr 2020 • Shuhang Wang, Szu-Yeu Hu, Eugene Cheah, XiaoHong Wang, JingChao Wang, Lei Chen, Masoud Baikpour, Arinc Ozturk, Qian Li, Shinn-Huey Chou, Constance D. Lehman, Viksit Kumar, Anthony Samir
This paper proposes a novel U-Net variant using stacked dilated convolutions for medical image segmentation (SDU-Net).
Modern deep learning algorithms geared towards clinical adaption rely on a significant amount of high fidelity labeled data.
Network structure and integrity can be controlled by a set of key nodes, and to find the optimal combination of nodes in a network to ensure network structure and integrity can be an NP-complete problem.
Differential evolution depends more heavily on the number of iterations, a relatively small population with more iterations can lead to better results.
Continual acquisition of novel experience without interfering previously learned knowledge, i. e. continual learning, is critical for artificial neural networks, but limited by catastrophic forgetting.
Moreover, pretraining is essential in reinforcement learning models, so we provide a high-quality annotated dataset for question reformulation by sampling a part of QuAC dataset.
The medical imaging literature has witnessed remarkable progress in high-performing segmentation models based on convolutional neural networks.
In this paper, we focus on identity fraud detection in loan applications and propose to solve this problem with a novel interactive dialogue system which consists of two modules.
Document Grounded Conversations is a task to generate dialogue responses when chatting about the content of a given document.
Clarifying user needs is essential for existing task-oriented dialogue systems.
This paper introduces INFaaS, a managed and model-less system for distributed inference serving, where developers simply specify the performance and accuracy requirements for their applications without needing to specify a specific model-variant for each query.
Enabling a mechanism to understand a temporal story and predict its ending is an interesting issue that has attracted considerable attention, as in case of the ROC Story Cloze Task (SCT).
In the guaranteed delivery scenario, ad exposures (which are also called impressions in some works) to users are guaranteed by contracts signed in advance between advertisers and publishers.