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

In this paper, we present a new approach to align sentences in bilingual parallel corpora based on the use of the linguistic information of the text pair in Gaussian mixture model (GMM) classifier. A feature parameter vector is extracted from the text pair under consideration. This vector contains text features such as length, punctuation score, cognate score and a bilingual lexicon extracted from the parallel corpus under consideration. A set of manually prepared training data has been assigned to train the Gaussian mixture model. Another set of data was used for testing. Using the Gaussian mixture model approach, we could achieve error reduction of 160% over length based approach when applied on English-Arabic parallel documents. In addition, the results of (GMM) outperform the results of the combined model which exploits length, punctuation, cognate and bilingual lexicon in a dynamic framework.

Text-based English-Arabic sentence alignment

In order to investigate the picture superiority effect, we compared the ERP between picture combined word (picture-word) and pure word (word) at study and test phase. During encoding, the FN400 was more negative and lasted longer for picture-words than for words. The late positive component (LPC) was more positive and distributed broadly for words compared to picture-words. During retrieval, the old picture-word elicited remarkably FN400 familiarity effect and parietal old/new effect compared to the old word. We suggested that simultaneous image and verbal encoding of picture-word elicited better and faster recollection compared to word during the memory test. Our findings also demonstrated that the picture superiority effect was related to the ability of pictures enhancing encoding and facilitating recollection.

The picture superiority effect in encoding and retrieval processes during Japanese learning for Chinese bilinguals

Enhancing Offensive Language Detection with Data Augmentation and Knowledge Distillation

In this paper, we report the work of TUA1 team in the dialogue evaluation (DialEval-2) task of NTCIR-16, which consists of two subtasks: the Dialogue Quality (DQ) subtask and the Nugget Detection (ND) subtask. Our proposed method consists of two parts: a feature extractor and a feedforward network. The feature extractor employs pre-trained Transformer networks to extract the hidden representations of the dialogue utterances and employs a Latent Dirichlet Allocation (LDA) method to extract the topic information of these utterances. The feedforward network then concatenates the hidden representations and the topics extracted by the feature extractor, compresses them through several feedforward layers into a desired dimension, and finally predicts the quality scores and nugget types of the dialogues. Since the DialEval-2 task dataset was composed of the one-to-one translated Chinese and English dialogues, we employ the pre-trained Transformer networks for Chinese and English, respectively, to extract the hidden representations of the dialogues. This makes it possible to process the sub-tasks on the Chinese or English datasets simultaneously. We train the neural network models based on the mean squared error for both dialogue quality prediction and nugget detection subtasks. Our proposed method reaches the best scores for RSNOD and NMD metrics in both Chinese and English dialogue quality subtasks among all participants. The results indicate that the proposed method is promising in learning a dialogue quality prediction system for generating very close predictions to the human annotators.

Fuji Ren

Papers

Text-based English-Arabic sentence alignment

The picture superiority effect in encoding and retrieval processes during Japanese learning for Chinese bilinguals

Enhancing Offensive Language Detection with Data Augmentation and Knowledge Distillation

TUA1 at the NTCIR-16 DialEval-2 Task c502147003@tokushima-u.ac.jpTokushimaUniversityTokushima,Japan

Efficient random subspace decision forests with a simple probability dimensionality setting scheme