新加坡南洋理工大学(南洋理工大学新加坡分校)是一所研究型公立大学,拥有工程、商业、科学、人文、艺术、社会科学、教育和医学的33000名本科生和研究生。

VIP内容

题目: Integrating Deep Learning with Logic Fusion for Information Extraction

摘要:

信息抽取(Information extraction, IE)旨在从输入文本中产生结构化的信息,例如命名实体识别和关系抽取。通过特征工程或深度学习为IE提出了各种尝试。然而,他们中的大多数人并没有将任务本身所固有的复杂关系联系起来,而这一点已被证明是特别重要的。例如,两个实体之间的关系高度依赖于它们的实体类型。这些依赖关系可以看作是复杂的约束,可以有效地表示为逻辑规则。为了将这种逻辑推理能力与深度神经网络的学习能力相结合,我们提出将一阶逻辑形式的逻辑知识集成到深度学习系统中,以端到端方式联合训练。该集成框架通过逻辑规则对神经输出进行知识正则化增强,同时根据训练数据的特点更新逻辑规则的权值。我们证明了该模型在多个IE任务上的有效性和泛化性。

作者:

Sinno Jialin Pan是南洋理工大学计算机科学与工程学院院长兼副教授,研究方向是迁移学习、数据挖掘、人工智能、机器学习。

成为VIP会员查看完整内容
0
34

最新内容

Recognizing an activity with a single reference sample using metric learning approaches is a promising research field. The majority of few-shot methods focus on object recognition or face-identification. We propose a metric learning approach to reduce the action recognition problem to a nearest neighbor search in embedding space. We encode signals into images and extract features using a deep residual CNN. Using triplet loss, we learn a feature embedding. The resulting encoder transforms features into an embedding space in which closer distances encode similar actions while higher distances encode different actions. Our approach is based on a signal level formulation and remains flexible across a variety of modalities. It further outperforms the baseline on the large scale NTU RGB+D 120 dataset for the One-Shot action recognition protocol by 5.6%. With just 60% of the training data, our approach still outperforms the baseline approach by 3.7%. With 40% of the training data, our approach performs comparably well to the second follow up. Further, we show that our approach generalizes well in experiments on the UTD-MHAD dataset for inertial, skeleton and fused data and the Simitate dataset for motion capturing data. Furthermore, our inter-joint and inter-sensor experiments suggest good capabilities on previously unseen setups.

0
0
下载
预览

最新论文

Recognizing an activity with a single reference sample using metric learning approaches is a promising research field. The majority of few-shot methods focus on object recognition or face-identification. We propose a metric learning approach to reduce the action recognition problem to a nearest neighbor search in embedding space. We encode signals into images and extract features using a deep residual CNN. Using triplet loss, we learn a feature embedding. The resulting encoder transforms features into an embedding space in which closer distances encode similar actions while higher distances encode different actions. Our approach is based on a signal level formulation and remains flexible across a variety of modalities. It further outperforms the baseline on the large scale NTU RGB+D 120 dataset for the One-Shot action recognition protocol by 5.6%. With just 60% of the training data, our approach still outperforms the baseline approach by 3.7%. With 40% of the training data, our approach performs comparably well to the second follow up. Further, we show that our approach generalizes well in experiments on the UTD-MHAD dataset for inertial, skeleton and fused data and the Simitate dataset for motion capturing data. Furthermore, our inter-joint and inter-sensor experiments suggest good capabilities on previously unseen setups.

0
0
下载
预览
Top