論文 - 萩原　将文

絵本の対話型生成支援システム

小柳壮摩，萩原将文

感性工学会論文誌 22 （ 2 ） 171 - 180 2023年04月

研究論文（学術雑誌）, 最終著者, 査読有り

　概要を見る

In this paper, we propose an interactive support system for generating picture books. The proposed system consists of two parts: a sentence generation part and a picture book image generation part. The sentence generation part takes a topic and an opening sentence of a picture book as inputs, and generates sentences of the picture book in an interactive manner. The user can select the most ap-propriate sentence from the generated sentences to create a story for the picture book, and can modify specific parts of the sentences. The image generation part generates a background image of the picture book using the text as an input, and acquires the necessary image objects for the picture book from the web. Using the retrieved images, the user can paste the image objects into the background image to create a picture book image. With these two parts, a picture book can be created without the user having to directly write the text and pictures. Through evaluation experiments, we confirmed that the proposed system can generate a picture book that is comfortable as a story and that can arouse the reader's interest.

• Access to Document (DOI)

外部知識によりパーソナライズされた対話システム

佐藤耕大，萩原将文

感性工学会論文誌 22 （ 2 ） 197 - 206 2023年04月

研究論文（学術雑誌）, 最終著者, 査読有り

　概要を見る

In this paper, we propose a new personalization method for a dialogue system using external knowledge and Graph Convolutional Networks (GCNs). The proposed system is divided into a personalize-part and a response-generation part with Japanese Transformer model. The personalize-part consists of a learned GCN, which can estimate the user’s interests, and a knowledge graph as external knowledge. The personalize-part can add an appropriate template to the response by Transformer according to the dialogue situation and user’s interests. Estimating a topic interesting for each user, the new system can provide an intimate dialogue reflecting individualized interests. We carried out extensive evaluation experiments, and it has shown that the proposed system exceeds the conventional Transformer dialogue model by 35.6% in the variety of information and by 34.0% in the level of desire to use the system.

• Access to Document (DOI)

論文サーベイ：「人々に寄り添う感性システム」をめざす研究動向

萩原将文

知能と情報 34 （ 3 ） 89 - 97 2022年08月

研究論文（学術雑誌）, 筆頭著者, 責任著者

• Access to Document (DOI)

CVAM: continuous-valued associative memory for one-to-many associations

Kano S., Hagiwara M.

Applied Intelligence （Applied Intelligence）  52 （ 5 ） pp.1-11 - 5472 2022年06月

研究論文（学術雑誌）, 共著, 最終著者, 責任著者, 査読有り,  ISSN  0924669X

　概要を見る

In this paper, we propose a CVAM (continuous-valued associative memory for one-to-many associations) with back-propagation learning and analyze the performance in detail. Conventional associative memories often deal with binary patterns, however, most of the data handled today are continuous-valued data. The basic architecture of the proposed CVAM is a three-layer perceptron with multiple sub-layers in the hidden layer. The multiple sub-layers enable one-to-many associations using back-propagation (BP) learning algorithm; each sub-layer memorizes single one-to-one association and the multiple sub-layers enables one-to-many associations. We carried out experiments to analyze the important properties such as memory capacity and noise tolerance performance using continuous-valued data. In addition, we conducted a demonstrative experiment to visually confirm the behavior of the proposed CVAM as an associative memory model using the CIFAR-10 image data set.

• Access to Document (DOI)
• Access to Document (DOI)

Deep-Learning-Based Fuzzy Symbolic Processing with Agents Capable of Knowledge Communication

Hiroshi Honda, Masafumi Hagiwara

International Conference on Agents and Artificial Intelligence (ICAART 2022)    1 - 8 2022年02月

研究論文（国際会議プロシーディングス）, 共著, 査読有り

スタイル変換を用いたYouTube動画タイトルの生成支援システム

小池隆斗，萩原将文

感性工学会論文誌 21 （ 1 ） 49 - 55 2022年02月

研究論文（学術雑誌）, 査読有り

オンラインカウンセリングサービスにおける対話の好感度分析

宮本千裕，萩原将文

感性工学会論文誌 21 （ 1 ） 105 - 112 2022年02月

研究論文（学術雑誌）, 査読有り

様々な概念に対する 関心の推定による知識グラフのパーソナライゼーション

佐藤耕大，萩原将文

感性工学会論文誌 21 （ 1 ） 57 - 64 2022年02月

研究論文（学術雑誌）, 査読有り

Multi-view Contrastive Multiple Knowledge Graph Embedding for Knowledge Completion

Kurokawa M., Yonekawa K., Haruta S., Konishi T., Asoh H., Ono C., Hagiwara M.

Proceedings - 21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022 （Proceedings - 21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022）     1412 - 1418 2022年

　概要を見る

Knowledge graphs (KGs) are useful information sources to make machine learning efficient with human knowledge. Since KGs are often incomplete, KG completion has become an important problem to complete missing facts in KGs. Whereas most of the KG completion methods are conducted on a single KG, multiple KGs can be effective to enrich embedding space for KG completion. However, most of the recent studies have concentrated on entity alignment prediction and ignored KG-invariant semantics in multiple KGs that can improve the completion performance. In this paper, we propose a new multiple KG embedding method composed of intra-KG and inter-KG regularization to introduce KG-invariant semantics into KG embedding space using aligned entities between related KGs. The intra-KG regularization adjusts local distance between aligned and not-aligned entities using contrastive loss, while the inter-KG regularization globally correlates aligned entity embeddings between KGs using multi-view loss. Our experimental results demonstrate that our proposed method combining both regularization terms largely outperforms existing baselines in the KG completion task.

• Access to Document (DOI)

Reproduction of Deep Reinforcement Learning Model with Fuzzy Symbolic Representation

Hiroshi Honda, Masafumi Hagiwaraa

International Symposium on Advanced Intelligent Systems (ISIS 2021)    1 - 6 2021年12月

研究論文（国際会議プロシーディングス）, 共著, 査読有り

共感と助言に着目した自動相談システム －恋愛相談を対象として－

磯島和樹，萩原将文

情報処理学会論文誌 62 （ 1 ） 378 - 386 2021年01月

研究論文（学術雑誌）, 査読有り

Analogical Reasoning with Deep Learning-Based Symbolic Processing

Honda H., Hagiwara M.

IEEE Access （IEEE Access）  9   121859 - 121870 2021年

研究論文（学術雑誌）, 査読有り

　概要を見る

The authors propose analogical reasoning systems based on first-order predicate logic using deep learning. The proposed systems consist of a model combining recursive neural networks and Word2Vec. When unknown data is input in this trained model, similar outputs to those of the trained data are obtained. Previous studies on symbolic inference using deep learning have focused on deductive and inductive inferences, and they require rule templates that are manually created and provided to the models in advance. However, it is not enough to infer unknown rules from a large amount of data on the Internet. Analogical reasoning is a mode of inference that attempts to solve a new case based on similarity. Thus, it enables inference of rules that were challenging to comprehend in previous studies. As a result of the experiments, unknown rules can be efficiently inferred from known rules contained in the knowledge bases. Using the proposed systems, the authors can extract unknown rules from five of the eight datasets consisting of three types of knowledge bases described in Prolog. The proposed method is the first case of analogical reasoning based on the first-order predicate logic using deep learning. Furthermore, the models used in the proposed systems have shown high robustness when using Word2Vec. For this reason, it is suggested that the practical applications of the proposed systems enable efficient inferences from a large amount of data that include noisy data on the Internet.

• Access to Document (DOI)

効果素材を付加した対話型漫画生成支援システム

鳥塚裕喜, 萩原将文

知能と情報 32 （ 6 ） 956 - 963 2020年12月

研究論文（学術雑誌）, 査読有り

Defense Against Adversarial Examples Using Quality Recovery for Image Classification

Motohiro Takagi, Masafumi Hagiwara

知能と情報 34 （ 4 ） 811 - 820 2020年08月

研究論文（学術雑誌）, 査読有り

A non-image-based subcharacter-level method to encode the shape of chinese characters

Ke Y., Hagiwara M.

Transactions of the Japanese Society for Artificial Intelligence （Transactions of the Japanese Society for Artificial Intelligence）  35 （ 2 ）  2020年

研究論文（学術雑誌）, 査読有り,  ISSN  13460714

　概要を見る

Most characters in the Chinese and Japanese languages are ideographic compound characters composed of subcharacter elements arranged in a planar manner. Token-based and image-based subcharacter-level models have been proposed to leverage the subcharacter elements. However, on the one hand, the conventional token-based subcharacter-level models are blind to the planar structural information; on the other hand, the image-based models are weak with respect to ideographic characters that share similar shapes but have different meanings. These characteristics motivate us to explore non-image-based methods to encode the planar structural information of characters. In this paper, we propose and discuss a method to encode the planar structural information by learning embeddings of the categories of the structure types. Our proposed model adds the structure embeddings to the conventional subcharacter embeddings and position embeddings before they are input into the encoder. In this way, the model learns the planar structural and positional information and retains the uniqueness of each character. We evaluated the method in a text classification task. In the experiment, the embeddings were encoded by a CNN encoder, and then the encoded vectors were input into an LSTM classifier to classify product reviews as positive or negative. We compared the proposed model with models that use only the subcharacter embeddings, the structure embedding or the position embeddings as well as with the conventional models in previous works. The results show that adding both structure embeddings and position embeddings leads to more rich and representative features and better fitting on the dataset. The proposed method results in at best 1.8% better recall, 0.63% better F-score, and 0.55% better accuracy on the testing datasets compared to previous methods.

• Access to Document (DOI)

単語の持つ感情推定法の提案と単語感情辞書の構築

武内達哉，萩原将文

感性工学会論文誌 18 （ 3 ） 273 - 278 2019年08月

研究論文（学術雑誌）, 査読有り

転移学習を用いた階層型潜在変数付きエンコーダ・デコーダによる自動相談システム

和田翔，萩原将文

感性工学会論文誌 18 （ 4 ） 307 - 307 2019年08月

研究論文（学術雑誌）, 査読有り

感性語を考慮した敵対的生成ネットワークを用いたロゴマーク生成

佐川友里香，萩原将文

感性工学会論文誌 18 （ 3 ） 215 - 222 2019年06月

研究論文（学術雑誌）, 査読有り

感情推定を利用した感性的な画像説明文自動生成システム

三由裕也, 萩原将文

感性工学会論文誌 18 （ 2 ） 151 - 158 2019年04月

研究論文（学術雑誌）, 共著, 査読有り

動的多層化ニューラルネットワーク

佐々木駿也，萩原将文

電子情報通信学会論文誌(D) J102-D （ 3 ） 226 - 234 2019年03月

研究論文（学術雑誌）, 査読有り