Open relation extraction (OpenRE) aims to extract relational facts from the open-domain corpus. To this end, it discovers relation patterns between named entities and then clusters those semantically equivalent patterns into a united relation cluster. Most OpenRE methods typically confine themselves to unsupervised paradigms, without taking advantage of existing relational facts in knowledge bases (KBs) and their high-quality labeled instances. To address this issue, we propose Relational Siamese Networks (RSNs) to learn similarity metrics of relations from labeled data of pre-defined relations, and then transfer the relational knowledge to identify novel relations in unlabeled data. Experiment results on two real-world datasets show that our framework can achieve significant improvements as compared with other state-of-the-art methods. Our code is available at https://github. com/thunlp/RSN.

Hyperbolic neural networks have shown great potential for modeling complex data. However, existing hyperbolic networks are not completely hyperbolic, as they encode features in the hyperbolic space yet formalize most of their operations in the tangent space (a Euclidean subspace) at the origin of the hyperbolic model. This hybrid method greatly limits the modeling ability of networks. In this paper, we propose a fully hyperbolic framework to build hyperbolic networks based on the Lorentz model by adapting the Lorentz transformations (including boost and rotation) to formalize essential operations of neural networks. Moreover, we also prove that linear transformation in tangent spaces used by existing hyperbolic networks is a relaxation of the Lorentz rotation and does not include the boost, implicitly limiting the capabilities of existing hyperbolic networks. The experimental results on four NLP tasks show that our method has better performance for building both shallow and deep networks. Our code is released to facilitate follow-up research 1 .

No abstract

eHealth literacy is the ability to access, assess, and use digital health information. This study compared the effects of a multimedia tutorial versus a paper-based control in improving older adults’ eHealth literacy from pre- to posttest. A total of 99 community-dwelling older adults (63–90 years old; mean = 73.09) participated from July 2019 to February 2020. Overall, knowledge about computer/Internet terms, eHealth literacy efficacy, knowledge about the quality of health information websites, and procedural skills in computer/Internet use improved significantly from pre- to posttest. No interaction effect was found between time and group. Participants in both groups had an overwhelmingly positive attitude toward training. Their attitudes toward training approached a statistically significant difference between the two conditions: F (1, 89) = 3.75, p = .056, partial η2 = .040, with the multimedia condition showing more positive attitudes. These findings have implications for designing effective eHealth literacy interventions for older adults.

Entity typing aims to classify semantic types of an entity mention in a specific context. Most existing models obtain training data using distant supervision, and inevitably suffer from the problem of noisy labels. To address this issue, we propose entity typing with language model enhancement. It utilizes a language model to measure the compatibility between context sentences and labels, and thereby automatically focuses more on context-dependent labels. Experiments on benchmark datasets demonstrate that our method is capable of enhancing the entity typing model with information from the language model, and significantly outperforms the stateof-the-art baseline. Code and data for this paper can be found from https://github. com/thunlp/LME.