Katsuyoshi Yamagami

Convolutional Neural Networks for Multi-topic Dialog State Tracking

The main task of the fourth Dialog State Tracking Challenge (DSTC4) is to track the dialog state by filling in various slots, each of which represents a major subject discussed in the dialog. In this article we focus on the ‘INFO’ slot that tracks the general information provided in a sub-dialog segment, and propose an approach for this slot-filling using convolutional neural networks (CNNs). Our CNN model is adapted to multi-topic dialog by including a convolutional layer with general and topic-specific filters. The evaluation on DSTC4 common test data shows that our approach outperforms all other submitted entries in terms of overall accuracy of the ‘INFO’ slot.

A multichannel convolutional neural network for cross-language dialog state tracking

The fifth Dialog State Tracking Challenge (DSTC5) introduces a new cross-language dialog state tracking scenario, where the participants are asked to build their trackers based on the English training corpus, while evaluating them with the unlabeled Chinese corpus. Although the computer-generated translations for both English and Chinese corpus are provided in the dataset, these translations contain errors and careless use of them can easily hurt the performance of the built trackers. To address this problem, we propose a multichannel Convolutional Neural Networks (CNN) architecture, in which we treat English and Chinese language as different input channels of one single CNN model. In the evaluation of DSTC5, we found that such multichannel architecture can effectively improve the robustness against translation errors. Additionally, our method for DSTC5 is purely machine learning based and requires no prior knowledge about the target language. We consider this a desirable property for building a tracker in the cross-language context, as not every developer will be familiar with both languages.

Collision avoidance path planning for hospital robot with consideration of disabled person's movement characteristic

A novel algorithm of collision avoidance path planning, especially for hospital robot, is proposed. The algorithm puts into consideration the movement characteristic of various kinds of disabled person, which are represented by wheelchair user and crutch user here. A model which implies the energy to move to a certain point from present location is introduced for each kind of disabled person. The model does not only consist of the distance to target point, but also the rotation angle and the persons easiness to change direction. Based on what kind of person the oncoming person is, the robot uses the appropriate model and estimates the easiest path for the person to move. Then, the robot plans an avoidance path.

Recurrent convolutional neural networks for structured speech act tagging

Spoken language understanding (SLU) is one of the important problem in natural language processing, and especially in dialog system. Fifth Dialog State Tracking Challenge (DSTC5) introduced a SLU challenge task, which is automatic tagging to speech utterances by two speaker roles with speech acts tag and semantic slots tag. In this paper, we focus on speech acts tagging. We propose local coactivate multi-task learning model for capturing structured speech acts, based on sentence features by recurrent convolutional neural networks. An experiment result, shows that our model outperformed all other submitted entries, and were able to capture coactivated local features of category and attribute, which are parts of speech act.