著者

西行 健太 日向 匡史 田崎 博 木下 航一 長谷川 友紀 山下 隆義 藤吉 弘亘

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.35, no.6, pp.C-K53_1-10, 2020-11-01 (Released:2020-11-01)

参考文献数

24

---

Driver pose estimation is a key component in driver monitoring systems, which is helpful for driver anomaly detection. Compared with traditional human pose estimation, driver pose estimation is required to be fast and compact for embedded systems. We propose fast and compact driver pose estimation that is composed of ShuffleNet V2 and integral regression. ShuffleNet V2 can reduce computational expense, and integral regression reduce quantization error of heat maps. If a driver suddenly gets seriously ill, the head of the driver is out of view. Therefore, in addition to localizing body parts, classifying whether each body part is out of view is also crucial for driver anomaly detection. We also propose a novel model which can localize and detect each body part of the driver at once. Extensive experiments have been conducted on a driver pose estimation dataset recorded with near infrared camera which can capture a driver at night. Our method achieves large improvement compared to the state-of-the-art human pose estimation methods with limited computation resources. Futhermore, We perform an ablation study of our method which composed of ShuffleNet V2, integral regression, and driver body parts detection. Finally, we show experimental results of each driver action for driver monitoring systems.

著者

高柳 俊祐 上條 敦史 石川 勉

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.27, no.5, pp.271-280, 2012 (Released:2012-09-04)

参考文献数

20

---

This paper presents a natural language processing tool, called CONV, which can translate Japanese sentences to well-formed formulas on an extended predicate logic, focusing on the knowledge representation scheme and the translating method to the scheme. This tool has been developed aiming to apply to several intelligent systems such as semantic information retrievers, dialogue systems and so on. In this tool, both a simple sentence and a complex sentence are represented by a single atomic formula, using ordinary words as predicate symbol and terms. Subordinate clauses in complex sentence are represented by embedded in the predicate or terms of the atomic formula for main clause, using the same form as main clause. Sentences are parsed using existent natural language processing tools and electronic dictionaries, and then are translated to logic formulas by newly developed rules.

著者

光田 航 東中 竜一郎 富田 準二

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.35, no.1, pp.DSI-E_1-10, 2020-01-01 (Released:2020-01-01)

参考文献数

27

---

Understanding the various information from user utterances is important for chat-oriented dialogue systems. However, no study has yet clarified the types of information that should be understood by such systems. With this purpose in mind, we first collected information that humans perceive from each utterance (perceived information) in chat-oriented dialogue. We then categorized the types of perceived information. The types were evaluated on the basis of inter-annotator agreement, which showed substantial agreement and demonstrated the validity of our categorization. To the best of our knowledge, this study is the first attempt to clarify the types of information that a chat-oriented dialogue system should understand from varied user utterances.

著者

伊藤 冬子 廣安 知之 三木 光範 横内 久猛

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.24, no.1, pp.127-135, 2009 (Released:2009-01-06)

参考文献数

16

被引用文献数

3 4

---

In interactive genetic algorithms (iGAs), computer simulations prepare design candidates that are then evaluated by the user. Therefore, iGA can predict a user's preferences. Conventional iGA problems involve a search for a single optimum solution, and iGA were developed to find this single optimum. On the other hand, our target problems have several peaks in a function and there are small differences among these peaks. For such problems, it is better to show all the peaks to the user. Product recommendation in shopping sites on the web is one example of such problems. Several types of preference trend should be prepared for users in shopping sites. Exploitation and exploration are important mechanisms in GA search. To perform effective exploitation, the offspring generation method (crossover) is very important. Here, we introduced a new offspring generation method for iGA in multimodal problems. In the proposed method, individuals are clustered into subgroups and offspring are generated in each group. The proposed method was applied to an experimental iGA system to examine its effectiveness. In the experimental iGA system, users can decide on preferable t-shirts to buy. The results of the subjective experiment confirmed that the proposed method enables offspring generation with consideration of multimodal preferences, and the proposed mechanism was also shown not to adversely affect the performance of preference prediction.

著者

鈴木 宏昭

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.19, no.2, pp.145-153, 2004 (Released:2004-01-27)

参考文献数

30

被引用文献数

5 1

---

The dynamic constraint relaxation theory predicts crucial roles of the initial diversity and evaluation in creative problem-solving. We reported the experimental evidence supporting these predictions, using an insight problem. The experiments showed that the degrees of making different types of trials and the appropriate evaluation were closely related to individual differences in insight problem-solving, and that evaluation became more appropriate by making the problem-solving goal explicit. The review of the research in related fields showed that these experimental findings were in congruent with the evidence obtained from different types of creative activities.

著者

北条 伸克 井島 勇祐 杉山 弘晃 宮崎 昇 川西 隆仁 柏野 邦夫

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.35, no.2, pp.A-J81_1-17, 2020-03-01 (Released:2020-03-01)

参考文献数

46

---

This paper aims at improving naturalness of synthesized speech generated by a text-to-speech (TTS) systemwithin a spoken dialogue system with respect to “how natural the system’s intention is perceived via the synthesizedspeech”. We call this measure “illocutionary act naturalness” in this paper. To achieve this aim, we propose toutilize dialogue-act (DA) information as an auxiliary feature for a deep neural network (DNN)-based speech synthesissystem. First, we construct a speech database with DA tags. Second, we build the proposed DNN-based speechsynthesis system based on the database. Then, we evaluate the proposed method by comparing its performance withtwo conventional hidden Markov model (HMM)-based speech synthesis systems, namely, the style-mixed modelingmethod and the style adaptation method. The objective evaluation results show that the proposed method overwhelmsthe style-mixed modeling method in the accuracy of reproduction of global prosodic characteristics of dialogue-acts.They also reveal that the proposed method overwhelms the style adaptation method in the accuracy of reproduction of sentence final tone characteristics of dialogue-acts. The subjective evaluation results also show that the proposed method improves the illocutionary act naturalness compared with the two conventional methods.

著者

中山 浩太郎 伊藤 雅弘 Maike ERDMANN 白川 真澄 道下 智之 原 隆浩 西尾 章治郎

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.24, no.6, pp.549-557, 2009 (Released:2009-10-20)

参考文献数

25

被引用文献数

5 4 2

---

Wikipedia, a collaborative Wiki-based encyclopedia, has become a huge phenomenon among Internet users. It covers a huge number of concepts of various fields such as arts, geography, history, science, sports and games. As a corpus for knowledge extraction, Wikipedia's impressive characteristics are not limited to the scale, but also include the dense link structure, URL based word sense disambiguation, and brief anchor texts. Because of these characteristics, Wikipedia has become a promising corpus and a new frontier for research. In the past few years, a considerable number of researches have been conducted in various areas such as semantic relatedness measurement, bilingual dictionary construction, and ontology construction. Extracting machine understandable knowledge from Wikipedia to enhance the intelligence on computational systems is the main goal of "Wikipedia Mining," a project on CREP (Challenge for Realizing Early Profits) in JSAI. In this paper, we take a comprehensive, panoramic view of Wikipedia Mining research and the current status of our challenge. After that, we will discuss about the future vision of this challenge.

著者

間瀬 久雄 絹川 博之 森井 洋 中尾 政之 畑村 洋太郎

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.17, no.1, pp.94-103, 2002 (Released:2002-04-04)

参考文献数

13

被引用文献数

6 5

---

This paper describes a system that directly supports a design process in a mechanical domain. This system is based on a thinking process development diagram that draws distinctions between requirement, tasks, solutions, and implementation, which enables designers to expand and deepen their thoughts of design. The system provides five main functions that designers require in each phase of the proposed design process: (1) thinking process description support which enables designers to describe their thoughts, (2) creativity support by term association with thesauri, (3) timely display of design knowledge including know-how obtained through earlier failures, general design theories, standard-parts data, and past designs, (4) design problem solving support using 46 kinds of thinking operations, and (5) proper technology transfer support which accumulates not only design conclusions but also the design process. Though this system is applied to mechanical engineering as the first target domain, it can be easily expanded to many other domains such as architecture and electricity.

著者

大澤 昇平 松尾 豊

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.29, no.5, pp.469-482, 2014

被引用文献数

1

---

In social networking service (SNS), popularity of an entity (e.g., person, company and place) roles an important criterion for people and organizations, and several studies pose to predict the popularity. Although recent papers which addressing the problem of predicting popularity use the attributes of entity itself, typically, the popularity of entities depends on the attributes of other semantically related entities. Hence, we take an approach exploiting the background semantic structure of the entities. Usually, many factors affect a person's popularity: the occupation, the parents, the birthplace, etc. All affect popularity. Predicting the popularity with the semantic structure is almost equivalent to solving the question: What type of relation most affects user preferences for an entity on a social medium? Our proposed method for popularity prediction is presented herein for predicting popularity, on a social medium of a given entity as a function of information of semantically related entities using DBpedia as a data source. DBpedia is a large semantic network produced by the semantic web community. The method has two techniques: (1) integrating accounts on SNS and DBpedia and (2) feature generation based on relations among entities. This is the first paper to propose an analysis method for SNS using semantic network.

著者

大澤 昇平 松尾 豊

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.31, no.2, pp.A-F24_1-10, 2016-03-01 (Released:2016-02-18)

参考文献数

22

---

Success of software developping project depend on skills of developers in the teams, however, predicting such skills is not a obvious problem. In crowd sourcing services, such level of the skills is rated by the users. This paper aims to predict the rating by integrating open source software (OSS) communities and crowd soursing services. We show that the problem is reduced into the feature construction problem from OSS communities and proposes the s-index, which abstract the level of skills of the developers based on the developed projects. Specifically, we inetgrate oDesk (a crowd sourcing service) and GitHub (an OSS community), and construct prediction model by using the ratings from oDesk as a training data. The experimental result shows that our method outperforms the models without s-index for the aspect of nDCG.

著者

宮崎 千明 平野 徹 東中 竜一郎 牧野 俊朗 松尾 義博 佐藤 理史

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.31, no.1, pp.DSF-E_1-9, 2016-01-06 (Released:2016-01-08)

参考文献数

13

---

Characterizing dialogue system utterances is important in making human-computer interaction systems more friendly and human-like. A method is described for achieving this by converting functional expressions according to their generation probabilities, which are calculated for specific characters. Experimental results show that the method can add characteristics of the target profiles (i.e., gender, age and closeness with a conversation partner) to dialogue system utterances and in so doing can generate a large variety of linguistic expressions.

著者

是枝 祐太 間瀬 久雄 柳井 孝介

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.34, no.5, pp.F-IC1_1-11, 2019-09-01 (Released:2019-09-01)

参考文献数

27

---

Japan Patent Office manually annotates submitted patents with F-terms (a patent classification scheme consisting of more than 300,000 labels) to aid search for prior patent applications. Keeping up the quality of F-term annotation is critical to patentability assessments, thus there is a demand for an automatic way to assist F-term annotation. One potential solution is to point out annotation mistakes by utilizing machine learning-based classification. However, the annotators cannot validate the predicted corrections because conventional classification methods do not give the rationales behind the corrections. Thus, the annotators may only adopt all or no corrections. The goal of this study was to assist F-term annotation by presenting annotators with corrections on the F-term annotation and the rationales behind the corrections.We proposed a joint neural model for F-term annotation and rationale identification. The proposed method incorporates a large portion of data annotated only with F-terms and a small portion of data annotated with rationales. It was first trained for F-term annotation, and then fine-tuned using the ground-truth rationales to discriminate rationales from non-rationales.We evaluated the proposed method on multiple F-terms from different technical domains. The proposed method outperformed baseline methods in terms of the rationale identification, implying that incorporating rationales in training is particularly useful in identifying rationales.

著者

小柴 等 森川 想

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.34, no.5, pp.E-J47_1-10, 2019-09-01 (Released:2019-09-01)

参考文献数

35

---

In this study, we attempt to reveal the relationship between the National Diet of Japan and Japanese ministries by text analysis of minutes data. The policy making process mainly consists of two routes: One is the parliamentary initiative route, and the other is the ministries initiative route, which is often consulted by advisory committees. These policy making process routes are not independent, but affect one another. While there are many studies and reports that have explored these relationships, most of them are qualitative case studies, which have some methodological limitations such as little comparability among cases.We propose a method of measuring the relationship between the National Diet of Japan and Japanese ministries through text similarity and time stamps contained within minutes of public organizations, which have been published online, providing machine-readable open data. Our analysis suggests that the method draws consistent results with existing qualitative analyses and can effectively support and improve understanding of the relationship between the Diet and ministries. In addition, this method has an advantage of analyzing a wide variety of topics using the same method, ensuring comparability for researchers.

著者

加藤 亜由美 深澤 佑介 森 武俊

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.30, no.1, pp.216-228, 2015-01-06 (Released:2015-01-06)

参考文献数

39

被引用文献数

2

---

Onomatopoeia appears much frequently in the word-of-mouth restaurant search site. In this paper, we first analyzed the relationship between food categories and onomatopoeias on the word-of-mouth restaurant search site. From the analysis, we found that the appearance of onomatopoeias and food categories are highly correlated. This fact indicates that na?ve way of using onomatopoeia as feature of restaurant makes the recommendation similar to food category based recommendation. This motivate us to develop sense related onomatopoeia based recommendation as senses plays an important role to enjoy food in restaurant. For the purpose, we propose an algorithm to collect sense related onomatopoeias from the web and produce serendipitous restaurant recommendation using sense related onomatopoeias as feature. We have conducted user test and the result shows that the recommendation using sense related onomatopoeia based recommendation satisfies 14 subjects from the viewpoint of serendipity, which is much larger than 3 subjects of food category based recommendation.

著者

高村 大也 奥村 学

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.23, no.6, pp.505-513, 2008 (Released:2008-09-17)

参考文献数

22

被引用文献数

3 3

---

We discuss text summarization in terms of maximum coverage problem and its variant. To solve the optimization problem, we applied some decoding algorithms including the ones never used in this summarization formulation, such as a greedy algorithm with performance guarantee, a randomized algorithm, and a branch-and-bound method. We conduct comparative experiments. On the basis of the experimental results, we also augment the summarization model so that it takes into account the relevance to the document cluster. Through experiments, we showed that the augmented model is at least comparable to the best-performing method of DUC'04.

著者

劉 超然 石井 カルロス寿憲 石黒 浩 萩田 紀博

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.28, no.2, pp.112-121, 2013 (Released:2013-01-17)

参考文献数

12

被引用文献数

1

---

A suitable control of head motion in robots synchronized with its utterances is important for having a smooth human-robot interaction. Based on rules inferred from analyses of the relationship between head motion and dialog acts, this paper proposes a model for generating head tilting and evaluates the model using different types of humanoid robots. Analysis of subjective scores showed that the proposed model can generate head motion with increased naturalness compared to nodding only or directly mapping people's original motions without gaze information. We also evaluate the proposed model in a real human-robot interaction, by conducting an experiment in which participants act as visitors to an information desk attended by robots. The effects of gazing control were also taken into account when mapping the original motion to the robot. Evaluation results indicated that the proposed model performs equally to directly mapping people's original motion with gaze information, in terms of perceived naturalness

著者

八木 勲 水田 孝信 和泉 潔

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.26, no.1, pp.208-216, 2011 (Released:2011-01-06)

参考文献数

16

被引用文献数

5 1

---

Since the subprime mortgage crisis in the United Sates, stock markets around the world have crashed, revealing their instability. To stem the decline in stock prices, short-selling regulations have been implemented in many markets. However, their effectiveness remains unclear. In this paper, we discuss the effectiveness of short-selling regulation using artificial markets. An artificial market that is an agent-based model of financial markets is useful to observe the market mechanism. That is, it is effective for analyzing causal relationship between the behaviors of market participants and the transition of market price. We constructed an artificial market that allows short-selling and an artificial market with short-selling regulation and have observed the stock prices in both of these markets. We have demonstrated that our artificial market had some properties of actual markets. We found that the market in which short-selling was allowed was more stable than the market with short-selling regulation, and a bubble emerged in the regulated market. We evaluated the values of assets of agents who used three trading strategies, specifically, these agents were fundamentalists, chartists, and noise traders. The fundamentalists had the best performance among the three types of agents.

著者

目良 和也 市村 匠 相沢 輝昭 山下 利之

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.17, no.3, pp.186-195, 2002 (Released:2002-04-04)

参考文献数

31

被引用文献数

6 21

---

There have been some studies about spoken natural language dialog,and most of them have successfully been developed within the speci ed task domains. However,current human-computer interfaces only get the data to process their programs.If the dialog processing has emotion comprehensive faculties, it should lead us to more human-like performance.In this paper,we present a method for constructing an emotion-handling dialog system in order to facilitate more confortable interaction with the users. We describe how to calculate emotions from the utterances,focusing on the similarities between the grammar structures and the semantic structures within the case frame.We made emotion generating calculations(EGC)to generate pleasure/displeasure emotion from an event.We also calculate the degree of the pleasure/displeasure from an opposite angle's length of the rectangular parallelepiped consisting of the all the terms in the EGC.EGC uses 8 type calculations for 12 event classi ed type by Okada. Word impressions about like/dislike are used for their calculations.Furthermore,we apply these calculations to the negatives and the noun phrases.To verify the e ectiveness of the proposed method,we tested some conversations using WWW-based health service system for elderly. We applied our method to 80 event in the conversations and calculated emotions almost corresponded to human-generating emotions.

著者

秋元 泰介 小方 孝

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.31, no.6, pp.AI30-O_1-8, 2016-11-01 (Released:2017-05-30)

参考文献数

54

---

Creativity is a challenging topic for artificial intelligence (AI) from the perspectives of both science and engineering. For engineering purposes, the manner in which creative AI systems provide values to humans and societies is a major concern that should be examined for the future development of AI technologies. The broader purpose of this study is to present a new direction of designing creative AI systems that consider their relationship with humans. We thus propose the basic design and concepts of a co-creative narrative generation system that produces diverse narratives through continual narrative generating chain reactions involving many agents. These agents include narrative generation programs and human narrative creators. The characteristics and significance of this design are discussed from several perspectives: 1) the relationship between generative programs and humans, 2) the design direction of narrative creativity, 3) the architectural aspect of a co-creative system for integrating many generative agents, and 4) knowledge construction in the narrative co-creation cycle.

著者

濱口 拓男 大岩 秀和 新保 仁 松本 裕治

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.33, no.2, pp.F-H72_1-10, 2018-03-01 (Released:2018-04-03)

参考文献数

31

被引用文献数

5

---

Knowledge base completion (KBC) aims to predict missing information in a knowledge base. In this paper, we address the out-of-knowledge-base (OOKB) entity problem in KBC: how to answer queries concerning test entities not observed at training time. Existing embedding-based KBC models assume that all test entities are available at training time, making it unclear how to obtain embeddings for new entities without costly retraining. To solve the OOKB entity problem without retraining, we use graph neural networks (GNNs) to compute the embeddings of OOKB entities, exploiting the limited auxiliary knowledge provided at test time. The experimental results show the effectiveness of our proposed model in the OOKB setting. Additionally, in the standard KBC setting in which OOKB entities are not involved, our model achieves state-of-the-art performance on the WordNet dataset.