著者

廣中 詩織 吉田 光男 岡部 正幸 梅村 恭司

出版者

人工知能学会

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence (ISSN:13460714)

巻号頁・発行日

vol.32, no.1, pp.WII-M_1-11, 2017

---

The home locations of Twitter users can be estimated using a social network, which is generated by various relationships between users. There are many network-based location estimation methods with user relationships. However, the estimation accuracy of various methods and relationships is unclear. In this study, we estimate the users’home locations using four network-based location estimation methods on four types of social networks in Japan. We have obtained two results. (1) In the location estimation methods, the method that selects the most frequent location among the friends of the user shows the highest precision and recall. (2) In the four types of social networks, the relationship of follower has the highest precision and recall.

著者

永井 秀幸 倉橋 節也

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.32, no.1, pp.D-G26_1-10, 2017-01-06 (Released:2017-01-13)

参考文献数

29

被引用文献数

3

---

In this paper, we propose an agent-based urban model in which the relationship between a central urban area and a suburban area is expressed simply. Allocation and bustle of a public facility where people stop off in daily life are implemented in the model. We clarify that transportation selection and their residence selection of residents make an effect to change the urban structure and environment. We also discuss how a compact urban structure and a reduction in carbon dioxide emissions are achieved with urban development policies and improvements on attractiveness of the facility for pedestrians and cyclists. In addition, we conduct an experiment of the exclusion of cars from the center of the city. The experimental results confirmed that the automobile control measure would be effective in decreasing the use of automobiles along with a compact urban structure.

著者

高橋 達二 甲野 佑 浦上 大輔

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-M_1-11, 2016-11-01 (Released:2016-12-26)

参考文献数

26

被引用文献数

3

---

As the scope of reinforcement learning broadens, the number of possible states and of executable actions, and hence the product of the two sets explode. Often, there are more feasible options than allowed trials, because of physical and computational constraints imposed on the agents. In such an occasion, optimization procedures that require first trying all the options once do not work. The situation is what the theory of bounded rationality was proposed to deal with. We formalize the central heuristics of bounded rationality theory named satisficing. Instead of the traditional formulation of satisficing at the policy level in terms of reinforcement learning, we introduce a value function that implements the asymmetric risk attitudes characteristic of human cognition. Operated under the simple greedy policy, the RS (reference satisficing) value function enables an efficient satisficing in K-armed bandit problems, and when the reference level for satisficing is set at an appropriate value, it leads to effective optimization. RS is also tested in a robotic motion learning task in which a robot learns to perform giant-swings (acrobot). While the standard algorithms fail because of the coarse-grained state space, RS shows a stable performance and autonomous exploration that goes without randomized exploration and its gradual annealing necessary for the standard methods.

著者

川島 貴広 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.20, no.5, pp.326-336, 2005 (Released:2005-07-05)

参考文献数

21

被引用文献数

3 5

---

We have developed a knowledge base of words as a tool to measure the semantic similarity between words. In this paper, we evaluate the knowledge base of words comparing with thesauruses, which are commonly used for measuring similarity. Thesauruses of NIHONGO-GOI-TAIKEI(NGT) and Japan Electronic Dictionary(EDR) are selected for the evaluation. For similarity calculation methods using thesauruses, we adopt a newly proposed method, in which each word is represented with vector using the structural feature of thesauruses and the degree of similarity between words is calculated by the inner product of their vectors, in addition to traditional methods based on the path length between categories or the depth of the subsumer. Evaluation is carried out through the two methods, that is, a traditional method based on human rating and the method we have already proposed, feasible for evaluating automatically without human judgment. Evaluation result shows that the knowledge base of word is superior to the both thesauruses(NGT outperforming EDR) as measurement tools, and the proposed calculation method outperforms the traditional ones. The result also shows that our evaluation method is a practical one, by investigating the correlation of both methods.

著者

桑原 教彰 桑原 和宏 安部 伸治 須佐見 憲史 安田 清

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.20, pp.396-405, 2005-11-01

参考文献数

22

被引用文献数

6 4

---

Providing good home-based care to people with dementia is becoming an important issue as the size of the elderly population increases. One of the main problems in providing such care is that it must be constantly provided without interruption, and this puts a great burden on caregivers, who are often family members. Networked Interaction Therapy is the name we call our methods designed to relieve the stress of people suffering from dementia as well as that of their family members. This therapy aims to provide a system that interacts with people with dementia by utilizing various engaging stimuli. One such stimulus is a reminiscence video created from old photo albums, which is a promising way to hold a dementia sufferer's attention for a long time. In this paper, we present an authoring tool to assist in the production of a reminiscence video by using photo annotations. We conducted interviews with several video creators on how they used photo annotations such as date, title and subject of photos when they produced the reminiscence videos. According to the creators' comments, we have defined an ontology for representing the creators' knowledge of how to add visual effects to a reminiscence video. Subsequently, we developed an authoring tool that automatically produces a reminiscence video from the annotated photos. Subjective evaluation of the quality of reminiscence videos produced with our tool indicates that they give impressions similar to those produced by creators using conventional video editing software. The effectiveness of presenting such a video to people with dementia is also discussed.

著者

芦川 将之 川村 隆浩 大須賀 昭彦

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.6, pp.503-515, 2014-11-01 (Released:2014-09-25)

参考文献数

25

被引用文献数

2

---

Open Crowdsourcing platforms like Amazon Mechanical Turk provide an attractive solution for process of high volume tasks with low costs. However problems of quality control is still of major interest. In this paper, we design a private crowdsourcing system, where we can devise methods for the quality control. For the quality control, we introduce four worker selection methods, each of which we call preprocessing filtering, real-time filtering, post processing filtering, and guess processing filtering. These methods include a novel approach, which utilizes a collaborative filtering technique in addition to a basic approach of initial training or gold standard data. For an use case, we have built a very large dictionary, which is necessary for Large Vocabulary Continuous Speech Recognition and Text-to-Speech. We show how the system yields high quality results for some difficult tasks of word extraction, part-of-speech tagging, and pronunciation prediction to build a large dictionary.

著者

中嶋 宏 森島 泰則 山田 亮太 Scott Brave Heidy Maldonado Clifford Nass 川路 茂保

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.3, pp.184-196, 2004 (Released:2004-04-06)

参考文献数

29

被引用文献数

4 15

---

In this information society of today, it is often argued that it is necessary to create a new way of human-machine interaction. In this paper, an agent with social response capabilities has been developed to achieve this goal. There are two kinds of information that is exchanged by two entities: objective and functional information (e.g., facts, requests, states of matters, etc.) and subjective information (e.g., feelings, sense of relationship, etc.). Traditional interactive systems have been designed to handle the former kind of information. In contrast, in this study social agents handling the latter type of information are presented. The current study focuses on sociality of the agent from the view point of Media Equation theory. This article discusses the definition, importance, and benefits of social intelligence as agent technology and argues that social intelligence has a potential to enhance the user's perception of the system, which in turn can lead to improvements of the system's performance. In order to implement social intelligence in the agent, a mind model has been developed to render affective expressions and personality of the agent. The mind model has been implemented in a human-machine collaborative learning system. One differentiating feature of the collaborative learning system is that it has an agent that performs as a co-learner with which the user interacts during the learning session. The mind model controls the social behaviors of the agent, thus making it possible for the user to have more social interactions with the agent. The experiment with the system suggested that a greater degree of learning was achieved when the students worked with the co-learner agent and that the co-learner agent with the mind model that expressed emotions resulted in a more positive attitude toward the system.

著者

稲葉 通将 吉野 友香 高橋 健一

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-F_1-9, 2016-01-06 (Released:2016-01-08)

参考文献数

23

被引用文献数

1

---

This paper presents an open domain monologue generation method for non-task-oriented dialogue systems to be able to speak their opinions and impressions as a speaker. To generate monologues, we acquire suitable utterances that contain a given topic from Twitter. Our method determines whether utterances have cohesion or not using the support vector machine and concatenate them in a row. It scores the utterance sequences from the aspect of their humor, unexpectedness and speciality in the given topic. We acquire the utterance sequences that ranks high as monologues. Results of an experiment demonstrate that our method can generate amusing and semantically appropriate monologues.

著者

濱崎 雅弘 武田 英明 大向 一輝 市瀬 龍太郎

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.19, no.5, pp.389-398, 2004 (Released:2004-07-06)

参考文献数

21

被引用文献数

2 4

---

In this paper, we discuss importance and utilization of personal network in a community system through the result of management and analysis of the scheduling support system for academic conferences. The important feature of the system is generation and utilization of personal network to support information exchanging and information discovery among participants. We applied this system to the academic conference called JSAI2003. We obtained 276 users and their personal networks. We found that (1) most participants were willing to contribute to form personal networks, (2) personal networks can promote information exchanging among participants since personal network showed existence of participants to the others and (3) the formed networks can was useful for them in information recommendation.

著者

大用 庫智 市野 学 高橋 達二

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.30, no.2, pp.403-416, 2015-01-01 (Released:2015-01-22)

参考文献数

65

被引用文献数

4 5 4

---

Cognitive psychology and behavioral economics have shown that humans have cognitive biases that deviate from normative systems such as classical logic and probability theory. Considering that humans have the ability to understand the world from sparse and/or imprecise data, it is natural to assume that the biases in human have some ecological merits in adaptation. We focus on two cognitive biases, symmetry and mutual exclusivity, that are considered peculiar to human. In this study, with the framework of empirical Bayes, we clarify the implication of a model of human causal cognition, the loosely symmetric (LS) model [Shinohara 07]) that implements the cognitive biases. We show that LS has great descriptive validity in inductive inference of causal relationship (causal induction) with a meta-analysis and an experiment in causal induction. The result of another experiment strongly suggests that humans use the inductively inferred causal relationship to decision-making. Then we show that LS effectively works in sequential decision-making under uncertainty (N-armed bandit problems). Operating LS as a simple value function under the greedy method in the framework of reinforcement learning, we analyze its behavior in terms of cognitive biases or heuristics under uncertainty. The three cognitive properties resulting from the loose symmetry, comparative valuation, satisficing, and prospect theory-like risk attitudes, are shown to be the key of the performance of LS. We parameterize the reference for satisficing and show that the quite intuitive parameter enables optimization.

著者

木村 大翼 久保山 哲二 渋谷 哲朗 鹿島 久嗣

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.3, pp.473-482, 2011 (Released:2011-04-19)

参考文献数

26

被引用文献数

2 12

---

Kernel method is one of the promising approaches to learning with tree-structured data, and various efficient tree kernels have been proposed to capture informative structures in trees. In this paper, we propose a new tree kernel function based on ``subpath sets'' to capture vertical structures in tree-structured data, since tree-structures are often used to code hierarchical information in data. We also propose a simple and efficient algorithm for computing the kernel by extending the Multikey quicksort algorithm used for sorting strings. The time complexity of the algorithm is O((|T_1|+|T_2|)log(|T_1|+|T_2|)) time on average, and the space complexity is O({|T_1|+|T_2|)}, where |T_1| and |T_2| are the numbers of nodes in two trees T_1 and T_2. We apply the proposed kernel to two supervised classification tasks, XML classification in web mining and glycan classification in bioinformatics. The experimental results show that the predictive performance of the proposed kernel is competitive with that of the existing efficient tree kernel proposed by Vishwanathan et al., and is also empirically faster than the existing kernel.

著者

高玉 圭樹 佐藤 史盟 大谷 雅之 服部 聖彦 佐藤 寛之 山口 智浩

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.210-219, 2013 (Released:2013-02-01)

参考文献数

12

被引用文献数

1

---

The paper proposes a novel recommender system which supports users to clarify the most appropriate preference by recommending other categories' items that almost meet the attributes selected by users. Such an advantage is achieved by both the preference ncretization of users and the preference change of users.To investigate the effectiveness of the proposed system, we conducted the human-subject experiments and found that the proposed system supports users to find their desirable items by clarifying their preference. Concretely, the following implications have been revealed: (1) the proposed recommender system with both the serendipity and decision buttons enables users to clarify their preference by comparing items which are classified in different categories; (2) in detail, the item recommendation based on the selected item attributes contributes to clarifying the users' preference through a change of their preference, while the item recommendation based on the item characteristic contributes to clarifying the users' preference through a concretization of their preference; and (3) the proposed recommender system with the decision button succeeds the further clarification of the preference of users who have already clarified it.

著者

小野 博紀 内海 彰

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.12-21, 2015-01-01 (Released:2015-01-06)

参考文献数

16

---

Causal knowledge is important for decision-making and risk aversion. However, it takes much time and effort to extract causal knowledge manually from a large-scale corpus. Therefore, many studies have proposed several methods for automatically extracting causal knowledge. These methods use a variety of linguistic or textual cues indicating causality on the basis of the assumption that causally related events tend to co-occur within a document. However, because of this assumption, they cannot extract causal knowledge that is not explicitly described in a document. Therefore, in this paper, we propose a novel method for extracting causal knowledge not explicitly described in a document using time series analysis of events. In our method, event expressions, which are represented by a pair of a noun phrase and a verb phrase, are extracted from newspaper articles. These extracted event expressions are clustered into distinct events, and the burst of the appearance of these clustered events is detected. Finally, using the time series data with burst, it is judged whether any event pairs have a causal relationship by Granger Causality test. We demonstrate through an evaluation experiment that the proposed method successfully extracts valid causal knowledge, almost all of which cannot be extracted by existing cue-based methods.

著者

今井 未来 水山 元

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

pp.I-F77, (Released:2015-12-16)

参考文献数

31

---

Recently, prediction markets are also used for estimating preferences, whose correct answer will not be revealed even after the market is closed, and, when used for the purpose, they are called preference markets. In order to utilize a preference market for estimating the attractiveness of product concepts expressed as combinations of various attributes, two technical questions remain to be answered. Firstly, how to estimate the preference on every possible combination of the attributes under consideration based on the results from a preference market comparing only a limited number of concepts? Secondly, how to incentivize the participants in the preference market to provide their estimation truthfully? This paper, therefore, develops a new product concept evaluation system by combining preference markets with conjoint analysis, and proposes three guidelines for how to determine the payoff for prediction securities. They are (1) to determine the payoff not directly from the security prices but indirectly through a model; (2) to run multiple markets in parallel if possible and use the results from all of them when determining the payoff; and (3) to use smoothed values instead of the final values as the security prices for determining the payoff. Moreover, the proposed system is tested with a simple evolutionary game simulation.

著者

三宅 貫太郎 福森 聡 杉原 太郎 五福 明夫 佐藤 健治

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.30, no.1, pp.148-151, 2015-01-05 (Released:2015-01-06)

参考文献数

7

被引用文献数

1

---

This article discusses the potential of Captology, a concept of the persuasive technologies, for long-term rehabilitation. Continuous rehabilitations to patients with chronic regional pain syndrome are an essential way to ameliorate the pain. Although the effects on a patient diminish when suspending the rehabilitation, he/she often feels resigned to keep it. Interference factors against the rehabilitation consist of difficulties to recognize the effects from the rehabilitation, interminable and repetitive rehabilitation, and complicated processes involving data collection for providing quality amelioration. Captology is one of promising concepts to solve these problems. We developed a set of functions with four principles from Captology, that is, Praise, Reduction, Tunneling and Self-Monitoring, into the system named VR/MVF for the sake of maintaining patient's motivation. One of the significant functions was developed to apply the principle of Praise. The system displays messages of praising/scolding to notice appropriate/inappropriate behaviors to him/her. The principles of Reduction and Tunneling were applied to reduce the burden of the system use. Tracking medical records by the principle of Self-Monitoring was employed to indicate the effects of rehabilitation to the patient.

著者

萩原 正人 小川 泰弘 外山 勝彦

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.3, pp.440-450, 2011 (Released:2011-04-01)

参考文献数

32

被引用文献数

1 1

---

Extraction of named entitiy classes and their relationships from large corpora often involves morphological analysis of target sentences and tends to suffer from out-of-vocabulary words. In this paper we propose a semantic category extraction algorithm called Monaka and its graph-based extention g-Monaka, both of which use character n-gram based patterns as context to directly extract semantically related instances from unsegmented Japanese text. These algorithms also use ``bidirectional adjacent constraints,'' which states that reliable instances should be placed in between reliable left and right context patterns, in order to improve proper segmentation. Monaka algorithms uses iterative induction of instaces and pattens similarly to the bootstrapping algorithm Espresso. The g-Monaka algorithm further formalizes the adjacency relation of character n-grams as a directed graph and applies von Neumann kernel and Laplacian kernel so that the negative effect of semantic draft, i.e., a phenomenon of semantically unrelated general instances being extracted, is reduced. The experiments show that g-Monaka substantially increases the performance of semantic category acquisition compared to conventional methods, including distributional similarity, bootstrapping-based Espresso, and its graph-based extension g-Espresso, in terms of F-value of the NE category task from unsegmented Japanese newspaper articles.

著者

和嶋 雄一郎 鷲田 祐一 冨永 直基 植田 一博

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.5, pp.409-419, 2013-09-01 (Released:2013-07-10)

参考文献数

26

被引用文献数

1

---

Previous studies of innovation have recognized that many innovations are developed by users. However, there is a risk of leaking new ideas by users who join a discussion to generate ideas. In order to avoid the risk, this study proposes a new workshop method to generate business ideas. In the workshop method, idea generators are required to discuss new business ideas based on information that is organized by users who do not join the discussion and thus never know new ideas that are created in this workshop. Idea generators who are given the user-organized information are considered to be able to create new ideas using the given information. We conducted an experiment to test this. In our experiment, participants were divided into two groups: the first group was asked to generate new business ideas based on the information with user perspective while the second group was asked to do so based on the information with engineer perspective. Performance of the first group was compared with that of the second group. Eight outside experts rated all ideas generated in terms of novelty, benefit and feasibility. The result showed that the ideas generated by the first group were rated significantly higher in terms of novelty as well as lower in terms of feasibility than the ideas generated by the second group. Furthermore, a questionnaire survey carried out to those who joined this workshop supported this finding. Our findings suggest that our workshop method is useful for bringing user perspective into actual business idea generation.

著者

原 一夫 鈴木 郁美 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.28, no.4, pp.379-390, 2013 (Released:2013-05-23)

参考文献数

27

---

We propose a new measure of semantic similarity between words in context, which exploits the syntactic/semantic structure of the context surrounding each target word. For a given pair of target words and their sentential contexts, labeled directed graphs are made from the output of a semantic parser on these sentences. Nodes in these graphs represent words in the sentences, and labeled edges represent syntactic/semantic relations between them. The similarity between the target words is then computed as the sum of the similarity of walks starting from the target words (nodes) in the two graphs. The proposed measure is tested on word sense disambiguation and paraphrase ranking tasks, and the results are promising: The proposed measure outperforms existing methods which completely ignore or do not fully exploit syntactic/semantic structural co-occurrences between a target word and its neighbors.

著者

横手 健一 ボレガラ ダヌシカ 石塚 満

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.220-229, 2013 (Released:2013-02-15)

参考文献数

33

被引用文献数

1 2

---

Predicting entailment between two given texts is an important task on which the performance of numerous NLP tasks such as question answering, text summarization, and information extraction depend.The degree to which two texts are similar has been used extensively as a key feature in much previous work in predicting entailment. However, using similarity scores directly, without proper transformations, results in suboptimal performance. Given a set of lexical similarity measures, we propose a method that jointly learns both (a) a set of non-linear transformation functions for those similarity measures and, (b) the optimal non-linear combination of those transformation functions to predict textual entailment. Our method consistently outperforms numerous baselines, reporting a micro-averaged F-score of 46.48 on the RTE-7 benchmark dataset. The proposed method is ranked 2-nd among 33 entailment systems participated in RTE-7, demonstrating its competitiveness over numerous other entailment approaches. Although our method is statistically comparable to the current state-of-the-art, we require less external knowledge resources.

著者

長谷川 隆明 西川 仁 今村 賢治 菊井 玄一郎 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.25, no.1, pp.133-143, 2010 (Released:2010-01-06)

参考文献数

16

被引用文献数

2

---

Recently, web pages for mobile devices are widely spread on the Internet and a lot of people can access web pages through search engines by mobile devices as well as personal computers. A summary of a retrieved web page is important because the people judge whether or not the page would be relevant to their information need according to the summary. In particular, the summary must be not only compact but also grammatical and meaningful when the users retrieve information using a mobile phone with a small screen. Most search engines seem to produce a snippet based on the keyword-in-context (KWIC) method. However, this simple method could not generate a refined summary suitable for mobile phones because of low grammaticality and content overlap with the page title. We propose a more suitable method to generate a snippet for mobile devices using sentence extraction and sentence compression methods. First, sentences are biased based on whether they include the query terms from the users or words that are relevant to the queries, as well as whether they do not overlap with the page title based on maximal marginal relevance (MMR). Second, the selected sentences are compressed based on their phrase coverage, which is measured by the scores of words, and their phrase connection probability measured based on the language model, according to the dependency structure converted from the sentence. The experimental results reveal the proposed method outperformed the KWIC method in terms of relevance judgment, grammaticality, non-redundancy and content coverage.