Search results

Entity relation extraction is an important research direction to obtain structured information. However, most of the current methods are to determine the relations between entities in a given sentence based on a stepwise method, seldom considering entities and relations into a unified framework. The joint learning method is an optimal solution that combines relations and entities. This paper aims to optimize hierarchical reinforcement learning framework and provide an efficient model to extract entity relation.

This paper is based on the hierarchical reinforcement learning framework of joint learning and combines the model with BERT, the best language representation model, to optimize the word embedding and encoding process. Besides, this paper adjusts some punctuation marks to make the data set more standardized, and introduces positional information to improve the performance of the model.

Experiments show that the model proposed in this paper outperforms the baseline model with a 13% improvement, and achieve 0.742 in F1 score in NYT10 data set. This model can effectively extract entities and relations in large-scale unstructured text and can be applied to the fields of multi-domain information retrieval, intelligent understanding and intelligent interaction.

The research provides an efficient solution for researchers in a different domain to make use of artificial intelligence (AI) technologies to process their unstructured text more accurately.

This paper aims to explore the transformation process and transformation mechanism of carbon steel under the marine environment.

In this paper, the transformation and rust layers corrosion products on 0Cu2Cr carbon steel with different cycles coupon test was investigated and deeply explored by scanning electron microscope, energy dispersive spectrometer, X-ray diffraction.

The results showed that the thickness of rust layers grew from 71.83 µm to 533.7 µm with increasing duration of corrosion. The initial corrosion product was γ-FeOOH, then part of the γ-FeOOH continued growing, and under the capillary action, the other part of the γ-FeOOH transformed to α-FeOOH.

To the best of the authors’ knowledge, this paper puts forward for the first time a new viewpoint of the development of corrosion products of low-carbon steel in two ways. This discovery provides a new idea for the future development of steel for marine engineering.

Commercial property market allows for the potential development of a similar real estate investment trust (REIT) structure in China as the commercial REITs (C-REIT) such as those offshore in Hong Kong and Singapore.

The authors examine tax codes of the present real estate investment methods in China in order to understand the interest for a new vehicle that specifically focuses on commercial real estate.

Given the progress of offshore C-REITS and Chinese government's emphasis on real estate, Chinese shareholders will benefit if onshore C-REITS are issued. Crucial to the success of C-REITS will be how the C-REIT shares will be priced with respect to Net Asset Value of underlying assets.

COVID-19 pandemic has changed government priorities, and development of C-REITS in real estate for growth may no longer be a priority policy for China.

Liquidity in real estate markets will be enhanced by C-REITS due to participation of private investors.

Onshore C-REITS would allow small and individual investors to have a stake in their home country's commercial real estate as an investment security for their own future.

This policy article also includes an interview with real estate professional in China whose opinions are embedded and added to the article.