This paper describes our submissions to task 7 in SemEval 2017, i.e., Detection and Interpretation of English Puns. We participated in the first two subtasks, which are to detect and locate English puns respectively. ...
详细信息
To model semantic similarity for multilingual and cross-lingual sentence pairs, we first translate foreign languages into English, and then build an efficient monolingual English system with multiple NLP features. Our...
详细信息
In this paper, a new image encryption algorithm is proposed by integrating Sine and piecewise linear chaotic maps. In order to realize the effect of encrypted image, the security key and 2D Sine-piecewise linear chaot...
详细信息
In this paper, a new image encryption algorithm is proposed by integrating Sine and piecewise linear chaotic maps. In order to realize the effect of encrypted image, the security key and 2D Sine-piecewise linear chaotic map (SPLCM) are used to encrypt the image by using random sequence and random matrix, and then using the replacement operation and the diffusion operation of the original image. The proposed image encryption algorithm is simple and practical, and the simulation results show that this algorithm is able to encrypt different types of digital images into unidentifiable random images. The security analysis also shows that this algorithm has a higher security level.
This paper reports our submission to subtask A of task 4 (Sentiment Analysis in Twitter, SAT) in SemEval 2017, i.e., Message Polarity Classification. We investigated several traditional Natural Language processing (NL...
详细信息
This paper describes the systems we submitted to the task 3 (Community Question Answering) in SemEval 2017 which contains three subtasks on english corpora, i.e., subtask A: Question-Comment Similarity, subtask B: Que...
详细信息
Aiming at the problem that the production process of corundum refractory is complex and the product quality cannot be predicted effectively, a quality forecasting model based on support vector regression is proposed i...
详细信息
This paper describes our submissions to task 8 in SemEval 2017, i.e., Determining rumour veracity and support for rumours. Given a rumoured tweet and a plethora of replied tweets, subtask A is to label whether these t...
详细信息
This paper studies the lack of systematic, teaching content and the obsolete teaching mode of the principle of computer composition in most colleges and universities in China. Proposed system-oriented teaching methods...
详细信息
This paper studies the lack of systematic, teaching content and the obsolete teaching mode of the principle of computer composition in most colleges and universities in China. Proposed system-oriented teaching methods and modes. This paper expounds the teaching goal of cultivating system competence based on classroom teaching system, supported by gradient experiment teaching, combining MOOC platform and SPOC teaching mode, and taking the second class as the teaching implementation system expanded.
The problem of counting crowds in varying density scenes or in different density regions of the same scene, named as pan-density crowd counting, is highly challenging. Previous methods are designed for single density ...
详细信息
Reinforcement learning algorithms are used to deal with a lot of sequential problems, such as playing games, mechanical control,and so on. Q-Learning is a model-free reinforcement learning *** traditional Q-learning a...
详细信息
Reinforcement learning algorithms are used to deal with a lot of sequential problems, such as playing games, mechanical control,and so on. Q-Learning is a model-free reinforcement learning *** traditional Q-learning algorithms, the agent stops immediately after it has reached the goal. We propose in this paper a new method—Experience-based Exploration method—in order to sample more efficient state-action pairs for Q-learning updating. In the Experience-based Exploration method, the agent does not stop and continues to search the states with high bellman-error inversely. In this setting, the agent will set the terminal state as a new start point, and generate pairs of action and state which could be useful. The efficacy of the method is proved analytically. And the experimental results verify the hypothesis on Gridworld.
暂无评论