著者

髙嶺 潮 遠藤 聡志

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.36, no.5, pp.B-KC6_1-9, 2021

---

<p>Scene understanding is a central problem in a field of computer vision. Depth estimation, in particular, is one of the important applications in scene understanding, robotics, and 3-D reconstruction. Estimating a dense depth map from a single image is receiving increased attention because a monocular camera is popular, small and suitable for a wide range of environments. In addition, both multi-task learning and multi-stream, which use unlabeled information, improve the monocular depth estimation efficiently. However, there are only a few networks optimized for both of them. Therefore, in this paper, we propose a monocular depth estimation task with a multi-task and multistream network architecture. Furthermore, the integrated network which we develop makes use of depth gradient information and can be applied to both supervised and unsupervised learning. In our experiments, we confirmed that our supervised learning architecture improves the accuracy of depth estimation by 0.13 m on average. Additionally, the experimental result on unsupervised learning found that it improved structure-from-motion performance.</p>

著者

鹿島 久嗣 坂本 比呂志 小柳 光生

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.21, no.1, pp.113-121, 2006 (Released:2006-01-06)

参考文献数

30

被引用文献数

1 1

---

We introduce a new convolution kernel for labeled ordered trees with arbitrary subgraph features, and an efficient algorithm for computing the kernel with the same time complexity as that of the parse tree kernel. The proposed kernel is extended to allow mutations of labels and structures without increasing the order of computation time. Moreover, as a limit of generalization of the tree kernels, we show a hardness result in computing kernels for unordered rooted labeled trees with arbitrary subgraph features.

著者

山田 康輔 笹野 遼平 武田 浩一

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.35, no.4, pp.B-K22_1-12, 2020

---

<p>It has been reported that a person's remarks and behaviors reflect the person's personality. Several recent studies have shown that textual information of user posts and user behaviors such as liking and reblogging the specific posts are useful for predicting the personality of Social Networking Service (SNS) users. However, less attention has been paid to the textual information derived from the user behaviors. In this paper, we investigate the effect of using textual information with user behaviors for personality prediction. We focus on the personality diagnosis website and make a large dataset on SNS users and their personalities by collecting users who posted the personality diagnosis on Twitter. Using this dataset, we work on personality prediction as a set of binary classification tasks. Our experiments on the personality prediction of Twitter users show that the textual information of user behaviors is more useful than the co-occurrence information of the user behaviors and the performance of prediction is strongly affected by the number of the user behaviors, which were incorporated into the prediction. We also show that user behavior information is crucial for predicting the personality of users who do not post frequently.</p>

著者

來村 徳信 中條 亘 笹嶋 宗彦 師岡 友紀 辰巳 有紀子 荒尾 晴惠 溝口 理一郎

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.36, no.4, pp.D-K94_1-16, 2021-07-01 (Released:2021-07-01)

参考文献数

32

---

For appropriate execution of human actions as a service, it is important to understand goals of the actions, which are usually implicit in the sequence-oriented process representations. CHARM (an abbreviation for Convincing Human Action Rationalized Model) has been proposed for representing such goals of the actions in a goal-oriented structure. It has been successfully applied for training novice nurses in a real hospital. Such a real-scale and general knowledge model, however, makes the learners difficult to understand which actions are important in a specific context such as a patient’s risk for complications. The goal of this research is to realize a context-adaptive knowledge structuring mechanism for emphasizing such actions that need special attention in a given context. As an extension of the CHARM framework, the authors have developed a general mechanism based on multi-goal action models and pathological mechanism models of abnormal phenomena. It has been implemented as a software system on tablet devices called CHARM Pad. We have also described knowledge models for the nursing domain, which include pathological mechanism models of complications with their risk factors. CHARM Pad with these models had been used by nursing students and evaluated by them through questionnaires. The result shows that CHARM Pad helped them understand the goals of nursing actions as well as finding of symptoms of complications context-adaptively.

著者

石原 一志 駒谷 和範 尾形 哲也 奥乃 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.20, no.3, pp.229-236, 2005 (Released:2005-03-23)

参考文献数

13

被引用文献数

2 2

---

Environmental sounds are very helpful in understanding environmental situations and in telling the approach of danger, and sound-imitation words (sound-related onomatopoeia) are important expressions to inform such sounds in human communication, especially in Japanese language. In this paper, we design a method to recognize sound-imitation words (SIWs) for environmental sounds. Critical issues in recognizing SIW are how to divide an environmental sound into recognition units and how to resolve representation ambiguity of the sounds. To solve these problems, we designed three-stage procedure that transforms environmental sounds into sound-imitation words, and phoneme group expressions that can represent ambiguous sounds. The three-stage procedure is as follows: (1) a whole waveform is divided into some chunks, (2) the chunks are transformed into sound-imitation syllables by phoneme recognition, (3) a sound-imitation word is constructed from sound-imitation syllables according to the requirements of the Japanese language. Ambiguity problem is that an environmental sound is often recognized differently by different listeners even under the same situation. Phoneme group expressions are new phonemes for environmental sounds, and they can express multiple sound-imitation words by one word. We designed two sets of phoneme groups: ``a set of basic phoneme group'' and ``a set of articulation-based phoneme group'' to absorb the ambiguity. Based on subjective experiments, the set of basic phoneme groups proved more appropriate to represent environmental sounds than the articulation-based one or a set of normal Japaneses phonemes.

著者

玉川 奨 香川 宏介 森田 武史 山口 高平

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.4, pp.386-395, 2014-07-01 (Released:2014-06-18)

参考文献数

8

被引用文献数

2

---

Here is discussed how to build up Japanese vocabulary for Japanese Linked Open Data. The vocabulary is constructed by mapping properties of the Japanese Wikipedia Ontology to the Linked Open Vocabularies. The Japanese Wikipedia Ontology is a large scale ontology learned from the Japanese Wikipedia. It includes many properties and property relations (property domains and property ranges). The Linked Open Vocabularies is a large cloud for vocabularies of Linked Open Data. We construct a Japanese vocabulary semi-automatically by mapping properties to vocabularies. Experimental case studies show us that we can use the built Japanese vocabulary as a general vocabulary for building Japanese Linked Open Data.

著者

関 陽介

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.36, no.2, pp.C-KA3_1-10, 2021-03-01 (Released:2021-03-01)

参考文献数

21

被引用文献数

2

---

Dialogue systems, which give users quick and easy access to required information interactively, have been widely used in various fields. Dialogue systems equipped with interfaces (e.g., humanoid robots and anthropomorphic agents) have been developed in order to enhance familiarity and dialogue continuity. Related studies, in which interactive agents generate humor expressions, have also been reported. Humor is indispensable for the formation of friendly relationships between people and systems, and humor expressions can be applied in situations that generate familiar responses and provide fun to users. In this study, in order to evoke humor through dialogue, a method to generate humorous expression by asking again due to pseudo mishearing of a part of users’ queries based on examples is proposed. Specifically, a conversion candidate dictionary for humor expressions, based on Wikipedia of Japanese edition and a classification vocabulary table in which words are classified semantically, is created by word completion using distributed representation. In addition, a word conversion method is designed by approximately 1,000 mishearing survey from Twitter, and the function based on the proposed method is implemented in a dialogue system introduced into a university as a model case. In the results of the comparative evaluation with other methods quantitatively, the proposed methods gave users the most humor by converting singular and multiple words. Thus, the effectiveness of the proposed method was clarified.

著者

橋口 友哉 山本 岳洋 藤田 澄男 大島 裕明

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.36, no.1, pp.WI2-B_1-13, 2021-01-01 (Released:2021-01-01)

参考文献数

25

---

In this study, we tackle the problem of retrieving questions from a corpus archived in a Community Question Answering service that a consultant having distress can feel empathy with them. We hypothesize that the consultant feels empathy with the questions having a similar situation with that of the consultant’s distress, and propose a method of retrieving similar sentences focusing on the situation of the distress. Specifically, we propose two approaches to fine-tuning the pre-trained BERT model so that the learned model better captures the similarity of the situation between distress. One tries to extract only the words representing the situation of the distress, the other tries to predict whether the two sentences show the same situation. The data for training the models are gathered by the crowdsourcing task where the workers are asked to gather the sentences whose situation is similar to the given sentence and to annotate the words in the sentences that represent the situation. The data is then used to fine-tune the BERT model. The effectiveness of the proposed methods is evaluated with the baselines such as TF-IDF, Okapi BM25, and the pre-trained BERT. The results of the experiment with 20 queries showed that one of our methods achieved the highest nDCG@5 while we could not observe any significant differences among the methods.

著者

西 朋里 小川 祐樹 高 史明 高野 雅典 森下 壮一郎 服部 宏充

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.36, no.1, pp.WI2-E_1-9, 2021

---

<p>With the rise of Internet TV and other new media, people are now viewing the news through a variety of conduits. In addition, the influence of news media on people is changing. Viewers can post comments in Internet TV, and these comments has the viewers' opinions of the news contents. Therefore, analysis of viewers comments is important in revealing the effect of the news. In addition, these comments are posted based on the morality of the viewers, and point of view of morality is considered important in the analysis of viewer comments in news. Therefore, this study purpose is to clarify the opinion on Internet TV news programs from a moral-based analysis viewers' comments. This study analyzed the trend of viewer comments on ABEMA news programs using comment length and the application of two methods. First, the morality of viewer comments was analyzed by calculating the moral/immoral expression rate for each program using the moral foundation dictionary. Second, the distributed expressions of viewer comments (calculated by Doc2Vec) were clustered by k-means++, and program trends were analyzed using the cluster characteristics. The results indicated that there was no difference in comment length between the two program types. Comments on soft-news programs had a high moral/immoral expression rate for politics or current events. In contrast, comments of hard-news programs did not show a characteristic trend. A viewer can easily participate in the discussion, because the soft-news program deals with the same news for a long time as the news content is limited compared to the non-discussion program.</p>

著者

古池 謙人 東本 崇仁 堀口 知也 平嶋 宗

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.5, pp.C-J82_1-17, 2020-09-01 (Released:2020-09-01)

参考文献数

29

被引用文献数

1

---

Recently, the demand for programming education is increasing worldwide. Enhancing intelligent tutoringsystems (ITSs) in programming education is therefore very important. For a computer to intelligently support suchlearning, it is desirable that it be adaptive to individual learning. In ITS research, learning effectiveness is enhancedby (A) controlling features of the question or problem to be asked by indexing based on characteristics of targetdomains, or by (B) making appropriate interventions such as feedback by grasping problem-solving processes basedon explainable problem-solving models.It is important to reuse knowledge acquired through problem-solving in programming. To reuse knowledge, itis effective to first understand differences between knowledge items and then to organize that knowledge. In programming,requirements become a problem to be solved. Requirements are defined separately in the software engineeringfield as functional requirements and non-functional requirements. Functional requirements are requirements for whatis satisfied, while non-functional requirements are characteristics for satisfying the functional requirements such asinterface or security. The purpose of this study is to organize the knowledge related to this process by regarding theachievement of functional requirements as problem-solving in programming.Assuming that problem-solving is directed toward acquisition of knowledge required for a solution, descriptionsof the programming knowledge itself lead to indexing of the problem. Some studies have utilized function–behavior–structure aspects, combining each aspect to handle knowledge in parts and using them for knowledge descriptions.We have considered that the problem-solving process in this programming can be explained according tothe definition of function–behavior–structure aspects. Therefore, we proposed a model of parts based on function–behavior–structure aspects. And, we further proposed a model of the problem-solving process of parts.In order to verify the effectiveness of feedback by the proposed models, an evaluation experiment was performedin comparison with the feedback by our previous system. Feedback by the proposed models is that can begenerated based on “parts management” function and “grasp behavior of structure” function of the ITS functions thatcan be realized by the proposed model.Experiment results are suggested that the proposed models can provide more appropriate feedback that can berealized in the system, suggesting that effective support can be realized through learning of parts under the proposedmodels.In this research, by defining programming knowledge as parts, we approach various elements related to programmingthat have previously been considered tacit and clarify and organize each element independently of theprogramming language used. In this way, we try to construct a model of the problem-solving process using partsfrom the viewpoint of learning and formalize tacit knowledge.

著者

牧野 拓哉 岩倉 友哉

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.B-K46_1-8, 2020-11-01 (Released:2020-11-01)

参考文献数

25

被引用文献数

1

---

Pointer-generator, which is the one of the strong baselines in neural summarization models, generates summaries by selecting words from a set of words (output vocabulary) and words in source documents. A conventional method for constructing output vocabulary collects highly frequent words in summaries of training data. However, highly frequent words in summaries could be usually a high possibility to be frequent in source documents. Thus, an output vocabulary constructed by the conventional method is redundant for pointer-generator because pointergenerator can copy words in source documents. We propose a vocabulary construction method that selects words included in each summary but not included in its source text of each pair. Experimental results on CNN/Daily Mail corpus and NEWSROOM corpus showed that our method contributes to improved ROUGE scores while obtaining high ratios of generating novel words that do not occur in source documents.

著者

中本 和岐 山田 悠 鈴木 英之進

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.18, no.3, pp.144-152, 2003 (Released:2003-03-04)

参考文献数

12

被引用文献数

1 2

---

This paper proposes a fast clustering method for time-series data based on average time sequence vector. A clustering procedure based on an exhaustive search method is time-consuming although its result typically exhibits high quality. BIRCH, which reduces the number of examples by data squashing based on a data structure CF (Clustering Feature) tree, represents an effective solution for such a method when the data set consists of numerical attributes only. For time-series data, however, a straightforward application of BIRCH based on a Euclidean distance for a pair of sequences, miserably fails since such a distance typically differs from human's perception. A dissimilarity measure based on DTW (Dynamic Time Warping) is desirable, but to the best of our knowledge no methods have been proposed for time-series data in the context of data squashing. In order to circumvent this problem, we propose DTWS (Dynamic Time Warping Squashed) tree, which employs a dissimilarity measure based on DTW, and compresses time sequences to the average time sequence vector. An average time sequence vector is obtained by a novel procedure which estimates correct shrinkage of a result of DTW. Experiments using the Australian sign language data demonstrate the superiority of the proposed method in terms of correctness of clustering, while its degradation of time efficiency is negligible.

著者

江上 周作 呂 暁東 古賀 禎 住谷 泰人

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.36, no.1, pp.WI2-F_1-12, 2021-01-01 (Released:2021-01-01)

参考文献数

28

---

With the advancement of information and communication technologies, to improve the interoperability between heterogeneous information systems by regularizing the syntax for information exchange is essential to achieve global seamless air traffic management operation. However, the current point-to-point aviation related information exchange among different systems and operators cannot satisfy the requirement for interoperability. The concept of System Wide Information Management (SWIM) has been promoted by the International Civil Aviation Organization (ICAO) to implement interoperability and harmonization in a global operation. In the SWIM environment, all the related stakeholders need to efficiently obtain the necessary ATM data with situational awareness from various information domains. However, this is difficult to realize in the current system, as different data are structured based on different data models. In this study, we construct domain ontologies based on flight, aeronautical, and weather information exchange models. Moreover, for semantic interoperability in the SWIM environment, we develop an upper ontology-based reference ontology that enables common situational awareness of spatiotemporal concepts. Furthermore, we propose a methodology for mapping heterogeneous domain ontologies to the reference ontology with the manual refinement. Finally, we apply the proposed ontologies to a SWIM test system. The applicability and scalability of the proposed ontologies are demonstrated through a case study in the SWIM environment.

著者

佐藤 大祐 松林 達史 足立 貴行 大井 伸哉 田中 悠介 長野 翔一 六藤 雄一 塩原 寿子 宮本 勝 戸田 浩之

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.35, no.2, pp.D-wd05_1-10, 2020-03-01 (Released:2020-03-01)

参考文献数

16

被引用文献数

2

---

In places where many people gather, such as large-scale event venues, it is important to prevent crowd accidentsfrom occurring. To that end, we must predict the flows of people and develop remedies before congestioncreates a problem. Predicting the movement of a crowd is possible by using a multi-agent simulator, and highly accurateprediction can be achieved by reusing past event information to accurately estimate the simulation parameters.However, no such information is available for newly constructed event venues. Therefore, we propose here a methodthat improves estimation accuracy by utilizing the data measured on the current day. We introduce a people-flowprediction system that incorporates the proposed method. In this paper, we introduce results of an experiment on thedeveloped system that used people flow data measured at an actual concert event.

著者

日高 昇平

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-H_1-10, 2016-11-01 (Released:2016-11-02)

参考文献数

30

---

A long-standing dream in research on artificial intelligence (AI) is to build a strong AI, which understands and processes the input, unlike a weak AI which just processes it as programmed. Toward realization of this dream, we need a mathematical formulation on what understanding is. In the present study, starting off by revisiting Shannon’s mathematical theory of communication, I argue that it is a model of information transmission but not that of information understanding, because of its common codebook shared by the sender and receiver. I outline the steps to build a model of information understanding, by seeking possibilities of decoding without the shared codebook. Given the model of information understanding, I discuss its relationship to other known problems in AI research, such as the symbol grounding problem and frame problem.

著者

蜷川 繁 米田 政明 広瀬 貞樹

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.16, no.2, pp.164-166, 2001 (Released:2002-02-28)

参考文献数

5

被引用文献数

2

---

The “Game of Life” acquires the property of significant behavior, such as universal computation, selforganized criticality and 1/f fluctuation, which depends on initial configurations. Our research investigates the relationship between the transient behavior starting from random initial configurations and array size in the Game of Life. The simulations show that the average transient time ‹T› increases logarithmically with square array size N×N, ‹T›∼logN in null and periodic boundary conditions. This result suggests that the duration of 1/f fluctuation in the “Game of Life” lengthens infinitely in infinite array size.

著者

細馬 宏通 坊農 真弓 石黒 浩 平田 オリザ

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.1, pp.60-68, 2014

被引用文献数

2

---

When the presence and the action of an android reach to those of human, andoroid can derive multi-modal action from human. How can human parties act with the android to organize the interaction and find the android as the social actor? We observed the development process of the play ``Three Sisters, Android Version'', and analyzed the multi-modal interaction between the android and human players in the process. As the result, the actors express the assessment of human likeness of the android with their utterances and body movements, and the border between human and machine was expressed with each modality in different way. Moreover, these expressions are not one-way product by the writer and director, but the product of repeated interactions between the actors and the android through the practice and rehearsals. Finally we discuss the possibility of ``media equation'' study using the direct observations of man-machine interaction.

著者

角森 唯子 東中 竜一郎 吉村 健 礒田 佳徳

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-B_1-10, 2020-01-01 (Released:2020-01-01)

参考文献数

23

---

A chat-oriented dialogue system can become more likeable if it can remember information about users and use that information during a dialogue. We propose a chat-oriented dialogue system that can use user information acquired during a dialogue and discuss its effectiveness on the interaction over multiple days. In our subjective evaluation over five consecutive days, we compared three systems: A system that can remember and use user information over multiple days (proposed system), one that can only remember user information within a single dialogue session, and another that does not remember any user information. We found that users were significantly more satisfied with our proposed system than with the other two. This paper is the first to verify the effectiveness of remembering on the interaction over multiple days with a fully automated chat-oriented dialogue system.

著者

吉川 友也 岩田 具治 澤田 宏

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.485-490, 2015-03-01 (Released:2015-03-05)

参考文献数

13

---

Group recommendation is a task to recommend items to groups such as households and communities. In this paper, we propose a non-linear matrix factorization method for group recommendation. The proposed method assumes that each member in groups has its own latent vector, and behavior of each group is determined by the probability distribution of the members' latent vectors. Recommending items is performed by using non-linear functions that map the distributions of the groups into scores for items. The non-linear functions are generated from Gaussian processes, which are defined by the similarities between distributions of the groups. We can efficiently calculate the similarities by embedding each distribution as an element in a reproducing kernel Hilbert space. We demonstrate the effectiveness of the method using two synthetic datasets and two real datasets in two prediction tasks.

著者

伊原 尚正 東藤 大樹 櫻井 祐子 横尾 真

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.5, pp.AG16-E_1-9, 2017-09-01 (Released:2017-09-01)

参考文献数

18

---

The cake cutting problem is concerned with the fair allocation of a divisible good among agents whose preferences vary over it. Recently, designing strategy-proof (SP) cake cutting mechanisms has caught considerable attention from AI and MAS researchers. Previous works assumed that an agent’s utility function is additive so that theoretical analysis becomes tractable. However, in practice, agents have non-additive utility over a resource. In this paper, we consider the all-or-nothing utility function as a representative example of non-additive utility because it can widely cover agents’ preferences for such real-world resources as the usage of meeting rooms, time slots for computational resources, bandwidth usage, and so on. We first show the incompatibility between envy-freeness (EF) and Pareto efficiency (PE) when each agent has all-or-nothing utility. We next propose a SP mechanism that satisfy PE, which is based on the serial dictatorship mechanism, at the sacrifice of EF. To address computational feasibility, we propose a heuristic-based allocation algorithm to find a near-optimal allocation in time polynomial in the number of agents, since the problem of finding a PE allocation is NP-hard. As another approach that abandons PE, we develop an EF and SP mechanism. Furthermore, we argue about false-name-proofness (FNP), which is the expansion of SP, and propose FNP and EF cake cutting mechanism. Finally, we evaluate our proposed mechanisms by computational experiments.