Search

Due to the national economic development form and social development demand, in recent years, the government has been vigorously promoting the control of government-enterprise collusion in the bidding process of government projects in order to promote the standardization of the market. How to predict the vertical collusion behavior under different internal and external environments has become an important research content. Although the prediction of individual behavior is difficult to achieve, the prediction of group behavior has certain possibilities. In this paper, we propose a method for predicting and evaluating the vertical collusion behavior of government investment project bidding based on BP neural network analysis optimized by an annealing algorithm. First, drawing on the traditional evaluation model, the evaluation index system of government-enterprise collusion behavior is constructed from five dimensions: internal environment, external environment, policy development, enforcement effort, and feedback channel. Secondly, a machine learning method based on BP neural network optimized by an annealing algorithm is introduced to evaluate the influence of the change of initial conditions on the bidding collusion behavior. This study has certain significance for government managers to discover the problems and causes in policy formulation, which in turn can support the government in further improving the policy utility.

Excellence in corporate culture is the key to achieving sustainable business development. Sustainability can be a source of success, innovation and profitability for a company, driving the achievement of low-carbon goals for transport infrastructure enterprises. The aim of this study is to examine the relationship between corporate culture and corporate sustainability from the perspective of transport infrastructure enterprises, and to identify which corporate culture factors may have an impact on the sustainable low carbon development of transport infrastructure enterprises. To achieve this, we constructed a structural equation model based on 351 cases in Hunan Province and examined the relationship between corporate culture and sustainable low-carbon development using partial least squares structural equation modeling. The findings suggest that corporate values and corporate culture management capabilities play an important role in promoting sustainable development of transport infrastructure enterprises at the economic and low-carbon levels.

The research on the evolution of the competition culture of highway construction enterprises aims to provide suggestions for highway construction enterprises to respond to the call of the Belt and Road Initiative and cope with overseas market competition in the new era. Based on the TF-IDF algorithm to extract the keywords of each enterprise culture, 291 enterprise culture texts were used as the analysis samples, and the evolution pattern of the competition culture of construction enterprises was explored. Relevant suggestions are made with the help of visualization and other technical means. It was found that: the competition culture of enterprises shows a trend from catering to the market to the internal construction of enterprises; the internal construction of enterprises is mainly reflected in talent competition, technological innovation and the optimization of management; the higher the level of competition, the more talent and technological innovation are valued; the development of competition culture is driven by the policy environment; and the focus of competition culture is affected by the maturity of the market.

In this paper, we propose a novel Human-like Semantic Cognition Network (HSCN) for aspect-level sentiment classification, motivated by the principles of human beings’ reading cognitive process (pre-reading, active reading, post-reading). We first design a word-level interactive perception module to capture the correlation between context words and the given target words, which can be regarded as pre-reading. Second, to mimic the process of active reading, we propose a targetaware semantic distillation module to produce the targetspecific context representation for aspect-level sentiment prediction. Third, we further devise a semantic deviation metric module to measure the semantic deviation between the targetspecific context representation and the given target, which evaluates the degree we understand the target-specific context semantics. The measured semantic deviation is then used to fine-tune the above active reading process in a feedback regulation way. To verify the effectiveness of our approach, we conduct extensive experiments on three widely used datasets. The experiments demonstrate that HSCN achieves impressive results compared to other strong competitors.

In the last decades, many similarity measures are proposed, such as Jaccard coefficient, cosine similarity, BM25, language model, etc. Despite the effectiveness of the existing similarity measures, we observe that none of them can consistently outperform the others in most typical situations. Choosing which similarity predicate to use is usually treated as an empirical question by evaluating a particular task with a number of different similarity predicates, which is not computationally efficient and the obtained results are not portable. In this paper, we propose a novel approach to combine different similarity predicates together to form a committee so that we do not need to worry about choosing which of them to use. Empirically, we can obtain a better result than any individual similarity predicate, which is quite meaningful in practice. Specifically, our method models the problem of committee generation as a 0–1 integer programming problem based on the confidence of similarity predicates and the reliability of attributes. We demonstrate the effectiveness of our model by applying it on three datasets with controlled errors. Experimental results demonstrate that our similarity predicate committee is more robust and superior over existing individual similarity predicates.

In order to improve the fault location accuracy of power cables, the two-side method is used for fault location. The main factors affecting the cable fault accuracy of the double-ended fault location method are the wave speed of traveling waves transmitted in the cable and the time difference between the traveling waves arriving at the monitoring equipment. In fact, traveling wave signals with different frequencies propagate at different wave speeds, and the use of fixed wave speeds for positioning calculations will inevitably cause positioning errors. First, the center frequency spectrum method is used to calculate the wave speed, and different wave speeds are used for different types of cables, so as to reduce the positioning error caused by the wave speed. Then, the devices on both sides use high-precision GPS to synchronize the time to reduce the natural error. For the time difference between the detected traveling waves reaching the devices on both sides, the triangle algorithm can be used to find the starting point for time difference calculation, thereby constructing a new cable fault location algorithm. Finally, a large number of PSCAD simulations and field discharge tests of cable grounding were carried out. The simulation results and test results verified the feasibility and superiority of this algorithm.

With the transformation of education from the traditional classroom environment to online education and assessment, it is more and more important to accurately assess the difficulty of questions than ever. As teachers may not be able to follow the student’s performance and learning behavior closely, a well-defined method to measure the difficulty of questions to guide learning is necessary. In this paper, we explore the concept of question difficulty and provide our new Chinese DT-QDC dataset. This is currently the largest and only Chinese question dataset, and it also has enriched attributes and difficulty labels. Additional attributes such as keywords, chapter, and question type would allow models to understand questions more precisely. We proposed the MTMS-BERT and ORMS-BERT, which can improve the judgment of difficulty from different views. The proposed methods outperforms different baselines by 7.79% on F1-score and 15.92% on MAE, 28.26% on MSE on the new DT-QDC dataset, laying the foundation for the question difficulty comprehension task.

Neural generation models have shown great potential in conversation generation recently. However, these methods tend to generate uninformative or irrelevant responses. In this paper, we present a novel topic-enhanced controllable CVAE (TEC-CVAE) model to address this issue. On the one hand, the model learns the context-interactive topic knowledge through a novel multi-hop hybrid attention in the encoder. On the other hand, we design a topic-aware controllable decoder to constrain the expression of the stochastic latent variable in the CVAE to reduce irrelevant responses. Experimental results on two public datasets show that the two mechanisms synchronize to improve both relevance and diversity, and the proposed model outperforms other competitive methods.

The sequence-to-sequence (Seq2Seq) model generates target words iteratively given the previously observed words during the decoding process, which results in the loss of the holistic semantics in the target response and the complete semantic relationship between responses and dialogue histories. In this paper, we propose a generic diversity-promoting joint network, called Holistic Semantic Constraint Joint Network (HSCJN), enhancing the global sentence information, and then regularizing the objective function with penalizing the low entropy output during the training stage. Our network introduces more target information to improve diversity and captures direct semantic information to better constrain relevance simultaneously. Moreover, the proposed method can be easily applied to any Seq2Seq structure. Extensive experiments on several dialogue corpuses show that our method effectively improves both semantic consistency and diversity of generated responses, and achieves better performance than other competitive methods.

Recent years have seen the dependency tree as effective information for relation extraction. Two problems still exist in previous methods: (1) dependency tree relies on external tools and needs to be carefully integrated with a trade-off between pruning noisy words and keeping semantic integrity; (2) dependency-based methods still have to encode sequential context as a supplement, which needs extra time. To tackle the two problems, we propose a faster dependency-free model in this paper: regarding the sentence as a fully-connected graph, we customize the vanilla transformer architecture to remove the irrelevant information via filtering mechanism and further aggregate the sentence information through the enhanced query. Our model yields comparable results on the SemEval2010 Task8 dataset and better results on the TACRED dataset, without requiring external information from the dependency tree but with improved time efficiency.

Analyzing public opinions towards products, services and social events is an important but challenging task. Despite the remarkable successes of deep neural networks in sentiment analysis, these approaches do not make full use of the prior sentiment knowledge (e.g., sentiment lexicon, negation words, intensity words). In this paper, we propose a Sentiment-Aware Attention Network (SAAN) to boost the performance of sentiment analysis, which adopts a three-step strategy to learn the sentiment-specific sentence representation. First, we employ a word-level mutual attention mechanism to model word-level correlation. Next, a phrase-level convolutional attention is designed to obtain phrase-level correlation. Finally, a sentence-level multi-head attention mechanism is proposed to capture various sentimental information from different subspaces. The experiments on Movie Review (MR) and Stanford Sentiment Treebank (SST) show that our model consistently outperform the previous methods for sentiment analysis.

Deep neural networks have gained great success recently for sentiment classification. However, these approaches do not fully exploit the linguistic knowledge. In this paper, we propose a novel sentiment lexicon enhanced attention-based LSTM (SLEA-LSTM) model to improve the performance of sentence-level sentiment classification. Our method successfully integrates sentiment lexicon into deep neural networks via single-head or multi-head attention mechanisms. We conduct extensive experiments on MR and SST datasets. The experimental results show that our model achieved comparable or better performance than the state-of-the-art methods.

Sentiment analysis of social media and comment data is an important issue in opinion monitoring. In this work, we propose a Linguistic-Aware Attention Network (LANN) to enhance the performance of convolution neural network (CNN). LANN adopts a two-stage strategy to model the sentiment-specific sentence representation. First, an interactive attention mechanism is designed to model word-level semantics. Second, to capture phrase-level linguistic structure, a dynamic semantic attention is adopted to select the crucial phrase chunks in the sentence. The experiments demonstrate that LANN has robust superiority over competitors and has reached the state-of-the-art performance.

In this study, we explore capsule networks with dynamic routing for text classification. We propose three strategies to stabilize the dynamic routing process to alleviate the disturbance of some noise capsules which may contain "background" information or have not been successfully trained. A series of experiments are conducted with capsule networks on six text classification benchmarks. Capsule networks achieve state of the art on 4 out of 6 datasets, which shows the effectiveness of capsule networks for text classification. We additionally show that capsule networks exhibit significant improvement when transfer single-label to multi-label text classification over strong baseline methods. To the best of our knowledge, this is the first work that capsule networks have been empirically investigated for text modeling., 12 pages