Data Mining - Concepts and Techniques.

We will review some of the major results in random graphs and some of the more challenging open problems. We will cover algorithmic and structural questions. We will touch on newer models, including those related to the WWW.

Random graphs

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Social Network Analysis

Emotion and Adaptation

There are many kinds of so-called irregular expressions in natural dialogues Even if the content of a conversation is the same in words, different meanings can be interpreted by a person's feeling or face expression To have a good understanding of dialogues, it is required in a flexible dialogue processing system to infer the speaker's view properly However, it is difficult to obtain the meaning of the speaker's sentences in various scenes using traditional methods In this paper, a new approach for dialogue processing that incorporates information from the speaker's face is presented We first divide conversation statements into several simple tasks Second, we process each simple task using an independent processor Third, we employ some speaker's face information to estimate the view of the speakers to solve ambiguities in dialogues The approach presented in this paper can work efficiently, because independent processors run in parallel, writing partial results to a shared memory, incorporating partial results at appropriate points, and complementing each other A parallel algorithm and a method for employing the face information in a dialogue machine translation will be discussed, and some results will be included in this paper© (2000) COPYRIGHT SPIE--The International Society for Optical Engineering Downloading of the abstract is permitted for personal use only

Parallel approach to incorporating face image information into dialogue processing

Textual emotion detection is playing an important role in the human-computer interaction domain. The mainstream methods of textual emotion detection are extracting semantic features and fine-tuning by language models. Due to the information redundancy in semantics, it is difficult for these methods to accurately detect all the emotions implied in the text. The prompting method has been shown to make the language models more purposeful in prediction by filling the cloze or prefix prompts defined. Therefore, we design a prompting method for multi-label classification. To stabilize the output, we design two consistency training strategies. We experiment on two multi-label emotion classification datasets: Ren-CECps and NLPCC2018. Our proposed prompting method with consistency training strategies for multi-label textual emotion detection (PC-MTED) model achieves state-of-the-art Macro F1 scores of 0.5432 and 0.5269, respectively. The experimental results indicate that our proposed method is effective in the multi-label textual emotion detection task. 

Prompt Consistency for Multi-label Textual Emotion Detection

Both Artificial Intelligence (AI) and Artificial Emotion (AE) have received much attention from academic as well as engineering circles. Structuralism, functionalism and behaviorism have been the three dominant approaches to the simulation of intelligence in history up to the present. All the approaches have made progress so far whereas they also, however, facing difficulties in their development. Further more, there have been no connections between the research in AI and that in AE. An attempt was thus made in the paper to propose another approach to the research in AI and AE. Different from the structuralism, functionalism and behaviorism, this approach is featured with the direct concern with the central mechanism of intelligence and emotion and is therefore termed mechanism approach. It is discovered as consequence that the transformations from information to knowledge and further to intelligence are the nucleus of the mechanism to AI and AE. A by-product that seems significant also achieved the same time that the three named approaches to AI can well be unified within the framework of mechanism approach. These discoveries, both AI and AE can successfully be simulated by mechanism approach and unifying the three approaches into harmonious one, may open up a new stage for the research in AI and AE as well as the integration of these two.

Mechanism approach to artificial intelligence and emotion research

Understanding of Chinese conventional expression is a big difficulty for the Japanese readers who want to know the natures of Chinese language and culture properly. Though most current researches are focusing on Chinese reading support, there is still no perfect system that can provide a convenient supporting aiming at Chinese conventional expressions. In this paper a practical Chinese conventional expression reading support system is presented from the viewpoint of recognition science. And we have also created a Chinese conventional expression database with 2305 conventional expressions of contemporary Chinese. At the same time we have analyzed the basic structures of these 2305 conventional expressions. By the analysis of the database we have classified three primary categories of these conventional expressions. Moreover, we have used the approach based on rules to recognize the Chinese conventional expressions.

Chinese conventional expression reading support system for Japanese

As an advanced method in the field of image segmentation, the fuzzy local information c-means (FLICM) algorithm has the problem of which segmentation performance is degraded when neighboring pixels are polluted, and it is imperfect for clustering nonlinear data. Focusing on these points, the Multi-kernel Collaboration-induced Fuzzy Local Information C-Means (MCFLICM) algorithm is put forward. To begin with, the concept of multi-kernel collaboration is introduced in image segmentation, and the Euclidean distance of the original space is replaced by multiple kernel-induced distance that are composed of multiple kernels in different proportions. Moreover, a new fuzzy factor is proposed from the viewpoints of pixel mean and local information, so as to increase the noises immunity. Finally, the multi-kernel collaboration and the new fuzzy factor are synthesized, and then the MCFLICM algorithm is put forward. MCFLICM can automatically adjust the requirements of different data points for kernel functions in the iterative procedure and can avoid the uncertainty of the selection of kernel function by the ordinary kernel algorithms. These advantages increase the robustness of the algorithm. In addition, MCFLICM has a stronger denoising performance to improve the ability to retain the original image details. Through comparing experiments with seven related algorithms, it is found that the segmentation performance of MCFLICM in binary image, three-valued image and natural image is superior to other algorithms, and the best results are achieved by MCFLICM from the viewpoints of visual effects and evaluation indexes.

Fuji Ren

Papers

Parallel approach to incorporating face image information into dialogue processing

Prompt Consistency for Multi-label Textual Emotion Detection

Mechanism approach to artificial intelligence and emotion research

Chinese conventional expression reading support system for Japanese

Multi-kernel Collaboration-Induced Fuzzy Local Information C-Means Algorithm for Image Segmentation