著者

宮西 大樹 関 和広 上原 邦昭

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.27, no.3, pp.223-234, 2012 (Released:2012-03-28)

参考文献数

32

---

This paper proposes a framework to predict future significance or importance of nodes of a network through link prediction. The network can be of any kind, such as a co-authorship network where nodes are authors and co-authors are linked by edges. In this example, predicting significant nodes means to discover influential authors in the future. There are existing approaches to predicting such significant nodes in a future network and they typically rely on existing relationships between nodes. However, since such relationships are dynamic and would naturally change over time (e.g., new co-authorship continues to emerge), approaches based only on the current status of the network would have limited potentiality to predict the future. In contrast, our proposed approach first predicts future links between nodes by multiple supervised classifiers and applies the RankBoost algorithm for combining the predictions such that the links would lead to more precise predictions of a centrality (significance) measure of our choice. To demonstrate the effectiveness of our proposed approach, a series of experiments are carried out on the arXiv (HEP-Th) citation data set.

著者

竹内 勇剛 中田 達郎

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.28, no.2, pp.131-140, 2013 (Released:2013-01-17)

参考文献数

20

---

Agency identification has been one of fundamental issue of Human-Agent Interaction studies. We carried out two experiments to examine what sort of behavior does make human identify the agency. And In order to examine agency identification, there was equipped an experimental environment for observing how people interpret other's behavior. The experimental environment which physically provided the interaction between human and computer was a media system that connects two sides of the experimental environment through the computer network. Therefore two persons can interact each other by using the own side's experimental environment that they can only touch and change color of the grid described to the screen. The task of experiment required participants to discriminate the other party if it was a human or a computer when they played the system. In this study, we regard attribution of humanlikeness toward other's behaviors as a sign of agency identification. The result of experiments showed that people can attributed humanlikeness toward other's behaviors when their actions were synchronized with other's actions such as rhythmical pattern and relation of spacial pattern. This result suggests that human agency identification is induced by interaction between the target entity and his/herself.

著者

梶野 洸 坪井 祐太 佐藤 一誠 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.28, no.3, pp.243-248, 2013 (Released:2013-03-13)

参考文献数

9

被引用文献数

2

---

Crowdsourcing services are often used to collect a large amount of labeled data for machine learning. Although they provide us an easy way to get labels at very low cost in a short period, they have serious limitations. One of them is the variable quality of the crowd-generated data. There have been many attempts to increase the reliability of crowd-generated data and the quality of classifiers obtained from such data. However, in these problem settings, relatively few researchers have tried using expert-generated data to achieve further improvements. In this paper, we apply three models that deal with the problem of learning from crowds to this problem: a latent class model, a personal classifier model, and a data-dependent error model. We evaluate these methods against two baseline methods on a real data set to demonstrate the effectiveness of combining crowd-generated data and expert-generated data.

著者

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

vol.27, no.6, pp.328-337, 2012 (Released:2012-09-27)

参考文献数

17

---

Many operational decisions of a company or an organization can be captured as a combinatorial optimization problem and, when the problem is clearly defined and appropriately formulated, it can be handled by a decision maker with the help of a suitable computerized algorithm. However, in a practical situation, it is often the case that the information required for clearly defining the problem is not fully available for a single decision maker but is dispersed among multiple stakeholders. This makes the problematic situation ill-defined and difficult to be dealt with properly by the decision maker alone. Thus, this paper takes up an undefinable shortest path problem as an example and proposes a prediction market approach for collectively solving it with a team of stakeholders. The approach aggregates the dispersed information on the problematic situation from the stakeholders through the market mechanism. After modeling the ill-defined situation by a shortest path problem with uncertainties in arc lengths, the paper discusses how to design the prediction security and market institution for collectively resolving the situation. Then, it conducts laboratory experiments to investigate how the proposed approach actually works. It further discusses how to generalize the approach to the case where the topology of the network is also uncertain.

著者

小松 孝徳 小林 一樹 山田 誠二 船越 孝太郎 中野 幹生

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.263-270, 2012 (Released:2012-08-30)

参考文献数

16

被引用文献数

1

---

Expressing the confidence level of a system's suggestions by using speech sounds is an important cue to users of the system for perceiving how likely it is for the suggestions to be correct. We assume that expressing confidence levels by using human-like expressions would cause users to have a poorer impression of the systems than if artificial subtle expressions (ASEs) were used when the quality of the presented information does not match the expressed confidence level. We confirmed that this assumption was correct by conducting a psychological experiment.

著者

田中 翔平 岡崎 直観 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.26, no.2, pp.366-375, 2011 (Released:2011-01-25)

参考文献数

26

---

This paper presents a novel method for acquiring a set of query patterns that are able to retrieve documents containing important information about an entity. Given an existing Wikipedia category that should contain the entity, we first extract all entities that are the subjects of the articles in the category. From these articles, we extract triplets of the form (subject-entity, query pattern, concept) that are expected to be in the search results of the query patterns. We then select a small set of query patterns so that when formulating search queries with these patterns, the overall precision and coverage of the returned information from the Web are optimized. We model this optimization problem as a Weighted Maximum Satisfiability (Weighted Max-SAT) problem. Experimental results demonstrate that the proposed method outperformed the methods based on statistical measures such as frequency and point-wise mutual information (PMI) being widely used in relation extraction.

著者

森近 憲行 濱崎 雅弘 亀田 尭宙 大向 一輝 武田 英明

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.2, pp.335-340, 2011 (Released:2011-01-06)

参考文献数

11

---

In this paper, we describe our approach for information extraction from documents, which is based on supervised machine learning and collective intelligence approach. This approach is aimed at redeeming each method, because each method has merits and demerits. It provides various ways for users to input data to improve information extraction. Users can add not only supervised data but also a rule to extract values for a set of attributes. Various ways to input data allows many users to add a lot of data for quality improvement and machine learning can reduce noise of data input by users. We implemented it in event-information extraction system, and the experimental result shows effectiveness in correctness and convenience.

著者

小西 克巳 遠山 敏章 渡辺 明日香

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.25-36, 2010 (Released:2010-01-06)

参考文献数

20

---

This paper proposes a fashion-related image gathering algorithm and a retrieval system. Since it is difficult to define the fashion-related image exactly in mathematical sense, computers can not recognize whether given images are fashion-related even if they use computer vision techniques. It is also difficult to gather and search only fashion-related images on the Internet automatically for the same reason. In order to overcome these difficulties, we focus on human computing power, which helps computers to find fashion-related images from tons of images on the Internet. This paper provides an algorithm to gather high quality fashion-related images and propses a fashion-related image retrieval system, both of which utilize the information and meta data obtained in a fashion-related image sharing site. Evaluation experiments show that the proposed algorithm can gather fashion-related images efficiently and that the proposed retrival system can find desired images more effectively than Google Image Search.

著者

岡田 将吾 賀 小淵 小島 量 長谷川 修

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.22, pp.493-507, 2007-11-01

被引用文献数

1

---

This paper presents an unsupervised approach of integrating speech and visual information without using any prepared data(training data). The approach enables a humanoid robot, Incremental Knowledge Robot 1 (IKR1), to learn words' meanings. The approach is different from most existing approaches in that the robot learns online from audio-visual input, rather than from stationary data provided in advance. In addition, the robot is capable of incremental learning, which is considered to be indispensable to lifelong learning. A noise-robust self-organized incremental neural network(SOINN) is developed to represent the topological structure of unsupervised online data. We are also developing an active learning mechanism, called ``desire for knowledge'', to let the robot select the object for which it possesses the least information for subsequent learning. Experimental results show that the approach raises the efficiency of the learning process. Based on audio and visual data, we construct a mental model for the robot, which forms a basis for constructing IKR1's inner world and builds a bridge connecting the learned concepts with current and past scenes.

著者

砂山 渡 高間 康史 ダヌシカ ボレガラ 西原 陽子 徳永 秀和 串間 宗夫 松下 光範

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.4, pp.483-493, 2011 (Released:2011-06-08)

参考文献数

34

被引用文献数

5

著者

和泉 潔 後藤 卓 松井 藤五郎

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.26, no.2, pp.313-317, 2011 (Released:2011-01-06)

参考文献数

12

被引用文献数

1

---

In this study, we propose a new text-mining method for long-term market analysis. Using our method, we performe out-of-sample tests using monthly price data of financial markets; Japanese government bond market, Japanese stock market, and the yen-dollar market. First we extract feature vectors from monthly reports of Bank of Japan. Then, trends of each market are estimated by regression analysis using the feature vectors. As a result of comparison with support vector regression, the proposal method could forecast in higher accuracy about both the level and direction of long-term market trends. Moreover, our method showed high returns with annual rate averages as a result of the implementation test.

著者

安村 禎明 武市 雅司 新田 克己

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.18, pp.212-220, 2003-11-01

被引用文献数

5 8

---

This paper introduces a support system for making presentation slides from a technical paper. This system provides functions that assign slides to each section and put objects on a slide. Inputs to this system are a technical paper as a TeX document, the number of slides that a user wants to make, and keywords of the paper. First, the system converts a paper from a TeX document into an XML document. The XML document can include information of a paper such as ID numbers and term weights. Next, the system calculates weights of terms in the document by the TF*IDF method. Based on the term weights, objects in the document such as sentences, figures and tables are weighted. Using the weights of the objects and slide composition templates, the system decides how many slides are assigned to each section. If a user does not like the assignment, she/he can reassign slides to the section using a presentation composition editor. Then, the system selects a layout for a slide considering the objects in the slide, and extracts objects arranged on the slide. The user can rearrange the objects on the slide using a slide editor. Finally, outputs of the system are generated as presentation slides in XHTML. From experimental results, we concluded our system is useful for making presentation slides.

著者

上田 洋 村上 晴美 辰巳 昭治

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.25, no.1, pp.144-156, 2010 (Released:2010-01-06)

参考文献数

17

被引用文献数

1

---

When users find information about people from the results of Web people searches, they often need to browse many obtained Web pages and check much unnecessary information. This task is time-consuming and complicates the understanding of the designated people. We investigate a method that integrates the useful information obtained from Web pages and displays them to understand people. We focus on curriculum vitae, which are widely used for understanding people. We propose a method that extracts event sentences from Web pages and displays them like a curriculum vita. The event sentence includes both time and events related to a person. Our method is based on the following: (1) extracting event sentences using heuristics and filtering them, (2) judging whether event sentences are related to a designated person by mainly using the patterns of HTML tags, (3) classifying these sentences to categories by SVM, and (4) clustering event sentences including both identical times and events. Experimental results revealed the usefulness of our proposed method.

著者

小町 守 牧本 慎平 内海 慶 颯々野 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.196-205, 2010 (Released:2010-01-06)

参考文献数

23

被引用文献数

2 2

---

As the web grows larger, knowledge acquisition from the web has gained increasing attention. Web search logs are getting a lot more attention lately as a source of information for applications such as targeted advertisement and query suggestion. However, it may not be appropriate to use queries themselves because query strings are often too heterogeneous or inspecifiec to characterize the interests of the search user population. the web. Thus, we propose to use web clickthrough logs to learn semantic categories. We also explore a weakly-supervised label propagation method using graph Laplacian to alleviate the problem of semantic drift. Experimental results show that the proposed method greatly outperforms previous work using only web search query logs.

著者

高野 敦子 池奥 渉太 北村 泰彦

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.24, no.3, pp.322-332, 2009

被引用文献数

3 2

---

Recently, the role of reputation information in on-line discussion groups and review sites has received much attention, and that has spurred a great deal of research on sentiment analysis of web documents. It is well known that collecting sentiment expressions, which tend to be domain-dependent, is useful for sentiment analysis. However, it can be prohibitively costly to manually collect expressions for each domain. The purpose of this paper is to propose an automatic method to acquire sentiment expressions on a specific subject from web documents.<BR> Our approach is based on a characteristic of sentiment expressions that often appear with their sentiment causes and both of them have cause-and-effect relationships. We develop a technique for recognizing cause-and-effect relationships between sentiment expressions and their sentiment causes using the results of dependency structure analysis. The proposed method uses this technique to extract sentiment causes starting from a small set of seed sentiment expressions, and extracts sentiment expressions from a set of sentiment causes. <BR> To evaluate this work, we conducted experiments using discussion board messages about hotels and sweets. The results demonstrate that the proposed method effectively extract diversified sentiment expressions relevant to each domain and possesses adequate precision. Precision is also found to be better for compound sentiment expressions.

著者

本村 陽一 西田 佳史

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.24, no.2, pp.284-294, 2009 (Released:2009-02-17)

参考文献数

32

被引用文献数

4 3

---

Human behavior understanding in everyday life is promising but not established research field. Our project named 'open life matrix' is focused on this field. In these years, many sensor houses and robotic room projects have been studied and sensing and network technology have been established. However, still we have problems to realize everyday life support information systems and services. There are two major problems. The first one is data representation and computational modeling problem in everyday life. The second one is that we don't have a good way to realize valuable services from research outcomes. We propose a challenge to solve these problems by a scheme for accumulating common data set and probabilistic causal modeling during everyday life services.

著者

中村 有作 舞田 哲哉 坂本 比呂志

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.22, no.2, pp.191-199, 2007 (Released:2007-01-25)

参考文献数

29

---

We propose an efficient algorithm for deciding the reachability between any nodes on XML data represented by connected directed graphs. We develop a technique to reduce the size of the reference table for the reachability test. Using the small table and the standard range labeling method for rooted ordered trees, we show that our algorithm answers almost queries in a constant time preserving the space efficiency and a reasonable preprocessing time.

著者

新出 尚之 高田 司郎 藤田 恵

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.13-24, 2011 (Released:2011-01-06)

参考文献数

16

被引用文献数

2 3

---

In multi-agent environments, to model cooperations among autonomous agents, many notions such as mutual beliefs and joint intentions, recognition of possibilities to achieve a goal with cooperation, and team formations, should be formally represented. In the traditional BDI logics, it is hard to treat them uniformly. We show the way to treat them uniformly using the fixed-point operator of the extended BDI logic \ omatoes. We also give some examples to apply it to the proof of some behaviors of multi-agent systems.

著者

小室 允人 船越 孝太郎

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.37, no.1, pp.A-L61_1-15, 2022-01-01 (Released:2022-01-01)

参考文献数

31

---

The questions "How human-like is this dialogue robot?" and "How natural was the conversation with this dialogue robot?" are major concerns for dialogue robot researchers and developers. However, they have overlooked the way that unique conversational structures exist in actual conversations between humans and dialogue robots, which are different from those between humans. In this paper, we focus on the repetition of the user's own speech, and the user's commenting in the absence of a robot's response, in a conversation with a dialogue robot. These phenomena are unique to conversations with dialogue robots. When the user's speech is not inputted into dialogue robots, users often repeat their own speech. In addition, when the repeated speech is also not inputted to the dialogue robot, users often comment on the absence of response from the robot by giving reasons why the robot does not respond. These phenomena are organized in order, which means the repetition is performed firstly, and if the repeated speech is not inputted, then secondly, users will comment on the absence of response from the robot. We analyze these situations using conversation analysis methods, and discuss how these phenomena are organized in order, and how these phenomena are unique to conversations with dialogue robots. In the last part of the paper, we reconsider the "human-likeness" of dialogue robots.

著者

上山 彩夏 狩野 芳伸

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.37, no.2, pp.G-L62_1-10, 2022-03-01 (Released:2022-03-01)

参考文献数

39

---

In recent years, there has been a lot of research on building dialogue systems using deep learning, which can generate relatively fluent response sentences to user utterances. Nevertheless, they tend to produce responses that are not diverse and which are less context-dependent. Assuming that the problem is caused by the Softmax Cross- Entropy (SCE) loss, which treats all words equally without considering the imbalance in the training data, a loss function Inverse Token Frequency (ITF) loss, which multiplies the SCE loss by a weight based on the inverse of the token frequency, was proposed and confirmed the improvement of dialogue diversity. However, in the diversity of sentences, it is necessary to consider not only the information of independent tokens, but also the frequency of incorporating a sequence of tokens. Using frequencies that incorporate a sequence of tokens to compute weights that dynamically change depending on the context, we can better represent the diversity we seek. Therefore, we propose a loss function, Inverse N-gram Frequency (INF) loss, which is weighted based on the inverse of the n-gram frequency of the tokens instead of the frequency of the tokens. In order to confirm the effectiveness of the proposed method on INF loss, we conducted metric-based and human evaluations of sentences automatically generated by models trained on the Japanese and English Twitter datasets. In the metric-based evaluation, Perplexity, BLEU, DIST-N, ROUGE, and length were used as evaluation indices. In the human evaluation, we assessed the coherence and diversity of the response sentences. In the metric-based evaluation, the proposed INF model achieved higher scores in Perplexity, DIST-N, and ROUGE than the previous methods. In the human evaluation, the INF model also showed superior values.