arXiv subjects

Toshiaki Takano

Publications and source records attributed to Toshiaki Takano.

3 recordsLinked to original sources

arXiv2022

The Analysis about Building Cross-lingual Sememe Knowledge Base Based on Deep Clustering Network

A sememe is defined as the minimum semantic unit of human languages. Sememe knowledge bases (KBs), which contain words annotated with sememes, have been successfully applied to many NLP tasks, and we believe that by learning the smallest unit of meaning, computers can more easily understand human language. However, Existing sememe KBs are built on only manual annotation, human annotations have personal understanding biases, and the meaning of vocabulary will be constantly updated and changed with the times, and artificial methods are not always practical. To address the issue, we propose an unsupervised method based on a deep clustering network (DCN) to build a sememe KB, and you can use any language to build a KB through this method. We first learn the distributed representation of multilingual words, use MUSE to align them in a single vector space, learn the multi-layer meaning of each word through the self-attention mechanism, and use a DNC to cluster sememe features. Finally, we completed the prediction using only the 10-dimensional sememe space in English. We found that the low-dimensional space can still retain the main feature of the sememes.

cs.CL↗

arXiv2016

Multimodal Hierarchical Dirichlet Process-based Active Perception

In this paper, we propose an active perception method for recognizing object categories based on the multimodal hierarchical Dirichlet process (MHDP). The MHDP enables a robot to form object categories using multimodal information, e.g., visual, auditory, and haptic information, which can be observed by performing actions on an object. However, performing many actions on a target object requires a long time. In a real-time scenario, i.e., when the time is limited, the robot has to determine the set of actions that is most effective for recognizing a target object. We propose an MHDP-based active perception method that uses the information gain (IG) maximization criterion and lazy greedy algorithm. We show that the IG maximization criterion is optimal in the sense that the criterion is equivalent to a minimization of the expected Kullback--Leibler divergence between a final recognition state and the recognition state after the next set of actions. However, a straightforward calculation of IG is practically impossible. Therefore, we derive an efficient Monte Carlo approximation method for IG by making use of a property of the MHDP. We also show that the IG has submodular and non-decreasing properties as a set function because of the structure of the graphical model of the MHDP. Therefore, the IG maximization problem is reduced to a submodular maximization problem. This means that greedy and lazy greedy algorithms are effective and have a theoretical justification for their performance. We conducted an experiment using an upper-torso humanoid robot and a second one using synthetic data. The experimental results show that the method enables the robot to select a set of actions that allow it to recognize target objects quickly and accurately. The results support our theoretical outcomes.

cs.RO↗

arXiv2000

Observations of Ammonia in External Galaxies. II. Maffei 2

The ammonia (J,K) = (1,1), (2,2), (3,3), and (4,4) transitions at 23.7 -- 24.1 GHz region were searched for in a nearby galaxy Maffei 2 to study relation between molecular abundances and physical conditions in galaxies. The (1,1), (2,2), and (3,3) emission lines were clearly detected. The rotational temperatures and ortho-to-para abundance ratios obtained are about 30 K and about 2.6, respectively. The abundance of NH3 relative to H2 in Maffei 2 was found to be the largest among galaxies where NH3 is already detected, and the abundance in Maffei 2 is more than an order of magnitude larger than the already reported upper limit in M82. Hence, we further confirmed the systematically peculiar molecular abundance in the aspect of formation mechanisms of molecules already reported in M82.

astro-ph↗