Re-examining lexical and semantic attention: Dual-view graph convolutions enhanced BERT for academic paper rating

Automatically assessing academic papers has enormous potential to reduce peer-review burden and individual bias. Existing studies strive for building sophisticated deep neural networks to identify academic value based on comprehensive data, e.g., academic graphs and full papers. However, these data are not always easy to access. And the content of the paper rather than other features outside the paper should matter in a fair assessment. Furthermore, while BERT models can maintain general semantics by pre-training on large-scale corpora, they tend to be over-smoothing due to stacked self-attention layers among unfiltered input tokens. Therefore, it is nontrivial to figure out distinguishable value of an academic paper from its limited content. In this study, we propose a novel deep neural network, namely Dual-view Graph Convolutions Enhanced BERT (DGC-BERT), for academic paper acceptance estimation. We combine the title and abstract of the paper as input. Then, a pre-trained BERT model is employed to extract the paper’s general representations. Apart from hidden representations of the final layer, we highlight the first and last few layers as lexical and semantic views. In particular, we re-examine the dual-view filtered self-attention matrices via constructing two graphs, respectively. After that, two multi-hop Graph Convolutional Networks (GCNs) are separately employed to capture pivotal and distant dependencies between the tokens. Moreover, the dual-view representations are facilitated by each other with biaffine attention modules. And a re-weighting gate is proposed to further streamline the dual-view representations with the help of the original BERT representation. Finally, whether the submitted paper could be acceptable is predicted based on the original language model features cooperated with the dual-view dependencies. Extensive data analyses and the full paper based MHCNN studies provide insights into the task and structural functions. Comparison experiments on two benchmark datasets demonstrate that the proposed DGC-BERT significantly outperforms alternative approaches, especially the state-of-the-art models like MHCNN and BERT variants. Additional analyses reveal significance and explainability of the proposed modules in the DGC-BERT. Our codes and settings have been released on Github (https://github.com/ECNU-Text-Computing/DGC-BERT).     

What Students Should Know About Technology: The Case of Scientific Visualization

Journal of Science Education and Technology - Starting with the focal question, “what should students know about technology?” we describe and illustrate a way of designing educational...     

量子超代数OSP_q(1,2)的参数化循环表示

本文依据量子超代数OSPq(1,2)的q变形玻色实现,在q变形Fock空间上得到了此代数的q玻色表示。通过引入一个p维线性空间,建立了此代数的参数化循环表示。     

Application of Cochlear Model in Speech Analysis/Synthesis Using Sinusoidal Representation

１　Ｉｎｔｒｏｄｕｃｔｉｏｎ　Ｗｉｔｈｔｈｅｄｅｖｅｌｏｐｍｅｎｔｏｆｉｎｆｏｒｍａｔｉｏｎｔｅｃｈｎｏｌｏｇｙ,ｓｐｅｅｃｈｔｒａｎｓｍｉｓｓｉｏｎａｎｄｓｐｅｅｃｈｓｔｏｒａｇｅｉｓｂｅｃｏｍｉｎｇｉｎｃｒｅａｓｉｎｇｌｙｉｍｐｏｒｔａｎｔ．Ａｃｃｏｒｄｉｎｇｔｏｔｈｅｐｒｅｓｅｎｔｄｅｖｅｌｏｐｍｅｎｔｏｆｄｉｇｉｔａｌｓｐｅｅｃｈｐｒｏｃｅｓｓｉｎｇ,ｄｅｖｅｌｏｐｍｅｎｔｏｆｓｐｅｅｃｈｃｏｄｉｎｇｍｅｔｈｏｄｓｗｉｔｈｈｉｇｈｃｏｄｉｎｇｅｆｆｉｃｉｅｎｃｙａｎｄｌｏｗｄｉｓｔ…     

有限典型空间中子空间包含的条件和矩阵表示

设IFnq 是有限域IFq 上的n维行向量空间 ,Gn 是IFq 上的n级典型群之一。IFnq 连同Gn 在它上的作用一起称为典型空间。综述有限典型空间中子空间包含的条件及矩阵表示。     

"再现说"的历史意义评说——兼谈文艺本质问题

在对文艺本质问题的探讨中,"再现说"影响深远.而对"再现说"产生背景和存在价值的评定则具有历史意义.本文着重探讨了"再现说"的发展概况、其内涵的合理和缺憾之处,同时也揭示了马克思主义对文艺本质内涵的界定.     

信息的表征和测度方法及应用研究

关于信息的概念 ,目前有许多说法。本文根据据“信息是对事物属性的表征”这一观点出发 ,提出了一种信息表征和测度的方法以及相应的信息测度公式 ,并讨论了信息测度公式的性质和这种信息表征和测度方法在基于内容的图像检索系统中的应用。     

群C4v酉表示中的佯谬

利用群表示的不同观点，可以消除存在于群Ｃ４ｖ的酉表示中的佯谬     

体育和媒体结合的社会文化审视——解读电视体育

以解读电视体育为主要研究目的,分析了体育与电视联姻并建立起共生关系的特质属性;探讨了电视如何按其自身准则在电视二维平面上重新构架体育,再现给受众的过程;从强调胜者世界、突出个性化、强化代理满足以及媒体文化奇观等方面解读了具有媒体文本意义的电视体育.     

联邦检索研究综述

[目的/意义] 对联邦检索研究进行梳理,总结发展现状,明确发展方向。[方法/过程] 在大量文献调研的基础上对联邦检索研究进行总结和评述。[结果/结论] 联邦检索包括数据集描述、数据集选择和结果合并3个阶段,各阶段从不同研究角度提出了较多算法,但缺乏权威的测试数据集和统一的评价标准。 联邦检索理论和技术被广泛应用,但大数据环境下也为其提出了许多新的研究课题。