著者

箕輪 峻 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.35, no.1, pp.DSI-F_1-13, 2020-01-01 (Released:2020-01-01)

参考文献数

17

---

Recently, end-to-end learning is frequently used to implement dialogue systems. However, existing systems still suffer from issues to handle complex dialogues. In this paper, we target on the conversation game “Mafia”, which requires players to make consistent and complex communications. We propose a middle language expression and a converter from natural language input. We implemented our dialogue system to play the Mafia game with humans and other automatic agents. Our evaluation on the play shows that our middle language increases conversion coverage.

著者

野田 恭平 高橋 久尚 津田 宏治 廣島 雅人

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.38, no.2, pp.E-M93_1-11, 2023-03-01 (Released:2023-03-01)

参考文献数

18

---

Due to the increase in material databases in recent years, there has been a lot of research regarding deep learning models which use large sizes of datasets and are aimed at the prediction of the material properties of inorganic compounds. Particularly, prediction models with Self-Attention structures, such as Roost and CrabNet, have garnered attention because of two reasons: (1) input variables are confined to the chemical composition of each formula and (2) Self-Attention enables models to learn individual element representations based on their chemical environment. However, the existing Self- Attention model yields low prediction accuracy when predicting structure-dependent material properties, such as the magnetic moment, for lack of structural information of compounds as input. In this research, based on the existing Self- Attention model, we set both elemental and structural information, especially the space group number and lattice constant, as input information and successfully construct a prediction model that is more versatile than existing methods. Furthermore, we visualized lists of promising materials by adopting Bayesian optimization. As a result, we have developed a system to propose desired materials for materials researchers.

著者

関根 由可里 中島 敬祐 大竹 景子 瀧沢 岳 杉山 淳一 向井 大誠 柿澤 恭史 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.38, no.2, pp.B-MA6_1-11, 2023-03-01 (Released:2023-03-01)

参考文献数

32

---

With the spread of COVID-19, the risk of droplet infection has been studied through interdisciplinary research. However, there is little information on the spread of the pathogen through human contact behavior. In this paper, we focus on the home, which is the private space of people, and propose a model to visualize the risk of contact infection to a family when people return home by combining calculation of contact behavior after returning home and study of virus transfer efficiency. First, from the contact behavior data for the first 30 minutes after returning home, we calculated the probability of flow line, the distribution of the number of contacts, the probability of initial action and the probability of contact behavior transmission. Next, we obtained the transfer efficiency between the substrate representing the household goods surface and the model skin, and the rate of change of the viral transfer efficiency when people continuously contact the household goods surface. According to these probabilities, we reproduced the state in which the virus attached to the hand or household goods surface by probabilistically performing the agent’s movement and contact behavior after returning home. This result shows that when agents return home with viruses attached to their hands, the viruses are widely confirmed on household goods surfaces. Furthermore, by simulating the combination and timing of hygienic actions such as handwashing and disinfection, it was possible to visualize their effects on the risk of re-contact and care effects.

著者

弘中 大介 横田 将生

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.18, no.5, pp.233-244, 2003 (Released:2003-06-10)

参考文献数

28

---

In general, it is not always easy for people to communicate each other comprehensively by limited information media. In such a case, employment of another information medium is very helpful and therefore cross-media translation is very important during such a communication. This paper presents the method and experiment of cross-media translation based on MIDST(Mental Image Directed Semantic Theory), where natural language texts about static positional relations of physical objects are systematically interpreted into 2-D pictures.

著者

岡留 有哉 阿多 健史郎 石黒 浩 中村 泰

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.6, pp.B-M43_1-13, 2022-11-01 (Released:2022-11-01)

参考文献数

30

---

Developing a communication agent that can mutually interact with a human has been expected. To realize the agent, real-time situation recognition and motion generation are necessary. The human-human interaction data is utilized to develop the recognition and the generation model. However, a cost of giving a certain label to the data is expensive, i.e., the number of labeled data becomes small. To cope with the small dataset problem, one of the approaches is to obtain the pre-trained weight by self-supervised learning. In this research, we propose estimating the amount of time-shift by “lag operation” as a task for self-supervised learning. The observed data is not isolated during the interaction between two people, and using both observed information from two people makes an estimation model reduce the uncertainty of situation detection. By exploiting these properties of interaction data, the time index of data of one person is shifted, i.e., the entrainment of two data is broken. This operation is called a “lag operation”, and estimating the amount of time-shift is defined as the pre-training task. We apply this pre-training to the prediction experiment that estimates near-future laughing during a conversation. The result shows the accuracy of the laughing prediction is improved by 1.3 points, and the lag operation is an effect for predicting the change of interaction situation.

著者

加藤 大貴 平山 高嗣 道満 恵介 井手 一郎 川西 康友 出口 大輔 村瀬 洋

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.D-KC7_1-10, 2021-09-01 (Released:2021-09-01)

参考文献数

18

---

The Japanese language is known to have a rich vocabulary of mimetic words, which have the property of sound symbolism; Phonemes that compose the mimetic words are strongly related to the impression of various phenomena. Especially, human gait is one of the most commonly represented phenomena by mimetic words expressing its visually dynamic state. Sound symbolism is useful for modeling the relation between gaits and mimetic words intuitively, but there has been no study on their intuitive generation. Most previous gait generation methods set specific class labels such as “elderly” but have not considered the intuitiveness of the generation model. Thus, in this paper, we propose a framework to generate gaits from a mimetic word based on sound symbolism. This framework enables us to generate gaits from one or more mimetic words. It leads to the construction of a generation model represented in a continuous feature space, which is similar to human intuition. Concretely, we train an encoder-decoder model conditioned by a “phonetic vector”, a quantitive representation of mimetic words, with an adaptive instance normalization module inspired by style transfer. The phonetic vector is a dense description of the intuitive impression of a corresponding gait and is calculated from many mimetic words in the HOYO dataset, which includes gait motion data and corresponding mimetic word annotations. Through experiments, we confirmed the effectiveness of the proposed framework.

著者

宮本 友樹 磐下 大樹 遠藤 水紀 永井 望 片上 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.36, no.5, pp.AG21-I_1-14, 2021-09-01 (Released:2021-09-01)

参考文献数

48

被引用文献数

3

---

In this paper, we investigate the acceptability of a non-task-oriented dialogue system that uses utterances to get closer psychologically. We defined utterances to get closer psychologically as “utterances that express intimacy with the other person or a favorable feeling toward the other person, such as joking, sympathy, compliment, or non-honorifics utterances (like a friend)”. Conventional research has reported that jokes, non-honorifics utterances, and compliments are useful for building a smooth relationship between a dialogue system and a user. On the other hand, individual differences in acceptability to utterances to get closer psychologically are considered to be large. In particular, we believe that the personality characteristics of the user affect the acceptability of utterances to get closer psychologically. So, we set research question 1: “How do user personality traits affect the acceptability of a non-task-oriented dialogue system with utterances get closer psychologically?” Also, utterances get closer psychologically has the risk of making the interlocutor uncomfortable. Therefore, in considering the implementation of utterances gets closer psychologically in a dialogue system, it is useful to examine how different strategies of utterances get closer psychologically affect the acceptability of a chatting dialogue system. So, we set research question 2: “How do different utterance strategies to get closer psychologically affect the acceptability of chatting dialogue systems?” To discuss these research questions, we conducted a dialogue experiment using a rule-based non-task-oriented dialogue system (n = 82). The results showed that for RQ1, among the five personality characteristics targeted in this experiment, the user’s diligence was related to the evaluation of the non-task-oriented dialogue system for utterance strategies to get closer psychologically used in this experiment in the subjective index, and extroversion, neurotic tendency, and openness in the objective index (likability based on user utterances). For research question 2, the experimental results showed that the acceptability between utterance strategies to get closer psychologically was significantly different in the viewpoint of the subjective index. These findings contribute to the design of a non-task-oriented dialogue system.

著者

Kei Wakabayashi Johane Takeuchi Mikio Nakano

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.37, no.3, pp.IDS-E_1-12, 2022-05-01 (Released:2022-05-01)

参考文献数

39

---

In language understanding for dialog systems, slot filling is a fundamental task usually formulated as a sequence labeling problem and solved using discriminative models such as conditional random fields and neural networks. One of the weak points of the discriminative approach is in the robustness against incomplete annotations, which are often generated in practice when we attempt to build large-scale training data. For making the slot filling algorithm more robust against the incompleteness of annotation, this paper leverages an overlooked property of slot filling tasks: Non-slot parts of utterance follow a specific pattern depending on the user’s intent. To reflect this idea, we propose a nonparametric Bayesian model that induces the grammatical role of the non-slot parts using a segmentation-based formulation of slot filling tasks. The proposed method can naturally deal with training data that includes incomplete annotations as a partially supervised grammar induction problem. The experimental result demonstrates that the proposed method estimates the slot information more accurately in a situation that the training data includes incomplete annotations in comparison to the BiLSTM-CRF and HMM.We also show that the proposed model has an advantage in the interpretability of the result of training and prediction by visualizing the parameters and the estimated labeled segmentations with a state transition diagram.

著者

森 大河 伝 康晴

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.3, pp.IDS-H_1-12, 2022-05-01 (Released:2022-05-01)

参考文献数

38

---

In human-human interactions, a listener uses both verbal tokens and head nods for responding signals, and they frequently co-occur. When humanoid robots and anthropomorphic agents response to a user using verbal tokens and head nods simultaneously, they must be generated in proper timing to each other and have consistent features. In this paper, we propose models to predict co-occurrence and physical features of head nods based on prosodic and syntactic features of verbal response tokens. We used, as predictive variables, the forms, positions, durations, averages/standard deviations of fundamental frequency and loudness of response tokens and head positions at the beginning of response tokens. In addition, considering participation framework, we also used speaker's gaze and listener's gaze at the beginning of response tokens, and applied generalized mixed models to predict the co-occurrence, type, range, repetition and velocity of head nods. The results confirmed that proposed models can predict these outcomes effectively.

著者

三野 星弥 吉川 雄一郎 伴 碧 石黒 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.37, no.3, pp.IDS-I_1-14, 2022-05-01 (Released:2022-05-01)

参考文献数

39

被引用文献数

2

---

The goal of this study is to realize a non-task-oriented dialogue agent that is accepted by people in the long term. One approach is using a dialogue strategy in which an agent shares information about other users who are not participating in the current dialogue. This study aims to develop a chatbot that is capable of sharing information about others and to examine its usefulness as well as its problems such as privacy concerns using a long-term empirical experiment in a real-world environment. The result of a 14-day experiment with 120 participants suggested that the usefulness of this dialogue strategy lies in its ability to maintain users’ motivation to interact with the agent and prevent them from having the impression that the agent is mechanical. However, irrespective of the presence of this dialogue strategy, it was suggested that the users were concerned about their privacy to the agent that collected their information on a daily basis. Based on these results, we discussed the relationship between the interestingness of the shared information and the users’ privacy concerns.

著者

薛 強 滝口 哲也 有木 康雄

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.3, pp.IDS-C_1-9, 2022-05-01 (Released:2022-05-01)

参考文献数

16

---

Generation-base dialogue system tends to produce generic response sentences. In order to improve the diversity of response sentences by the generation-base dialogue system, the response text retrieved by the retrieval-base model can be input to the generation-base model as reference response text, so that the generation-base model can generate highly diverse response sentences. However, the prior works show that the generation-base dialogue system often ignores the reference response text, resulting in the response sentences that is unrelated to the reference response text. In this work, we propose the Dialogue-Filling method, which can utilize 100% of the reference response text by masking the response sentences with a text-filling technique. We built variants of Dialogue-Filling method with DialoGPT model. Experiments on the DailyDialog Dataset demonstrate that our Dialogue-Filling method outperforms the baseline method on the dialogue generation task.

著者

宮本 友樹 永井 望 満田 雄斗 磐下 大樹 遠藤 水紀 鈴木 章弘 片上 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.37, no.3, pp.IDS-G_1-16, 2022-05-01 (Released:2022-05-01)

参考文献数

37

---

In this paper, we propose the “Risky Politeness Strategy (RPS)” as a framework of utterance strategy focusing on risk-taking in dialogue systems. In previous research, it has been reported that it is useful to implement politeness strategies that have risks such as jokes and compliments in dialogue systems. On the other hand, a design theory for effectively implementing risk-taking utterance strategies in dialogue systems has not been established. Against this background, we defined RPS with reference to politeness/impoliteness research in the fields of linguistics. In addition, we developed a rule-based dialogue system and an example-based dialogue system to implement the RPS in a non-task-oriented dialogue. User evaluations were conducted through the preliminary rounds of the Dialogue System Live Competition 2 and 3. The results of the user evaluations showed that the rule-based and example-based RPS-speaking non-task-oriented dialogue systems were able to engage in dialogue that was evaluated by the user as having humanity. Therefore, the usefulness of implementing RPS in non-task-oriented dialogue systems has been shown at a certain level.

著者

市川 淳 三輪 和久 寺井 仁

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.3, pp.585-594, 2015-05-01 (Released:2015-05-01)

参考文献数

25

被引用文献数

3 1

---

For skill acquisition that needs periodic body movements as cascade juggling, the establishment of stable body movements seems crucial. We investigated them in each of the learning stages defined by the Beek and van Santvoord (1992) framework. In addition, we investigated participants' verbal reports about what was intentionally concerned for achieving optimum learning in practice. In the experiment, novices practiced three-ball cascade juggling over a period of one week. We focused on two types of stabilities: the stability of chest movement representing torso movement, and another stability of wrist movement representing arm swing. The result revealed that the skills for establishing stabilities of torso movement and arm swing were acquired sequentially. In this case, the stability of arm swing emerged between Stage 2 (by 50 successive catches) and Stage 3 (by over 100 successive catches), and another stability of torso movement emerged between Stage 3 and the expert stage in which jugglers had acquired complete skills for performing five-ball cascade juggling. The result also showed that in the establishment of stable arm swing, the development of the stability occurred only in passive catching behavior, but did not in active tossing behavior. Additionally, we found that the participants who did not develop beyond Stage 1 (by 10 successive catches) trained themselves while focusing on their specific physical movements.

著者

水門 善之 田邊 洋人

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.37, no.2, pp.37-2_D-LB2, 2022-03-01 (Released:2022-03-01)

参考文献数

12

---

In recent years, the importance of responding to climate change has increased, and various countries have set greenhouse gas emission reduction targets centered on CO₂ (Carbon Dioxide). In this study, we analyzed the relationship between macroeconomic activity and CO₂ emissions amid growing discussions on CO₂ emissions. Recently, while the positive correlation between GDP and CO₂ emissions on a level basis, which had been confirmed in the past, is collapsing mainly in Europe and the United States. However, it this research, we converted the GDP and CO₂ emissions data to a yearly change rate in order to mitigate the effects of structural environmental changes and we confirmed that a positive correlation was maintained between emissions and economic growth rate. Then, in this research, in order to immediately grasp the CO₂ emission status, we used the CO₂ concentration data which was measured using the observation information from artificial satellites (GOSAT, Greenhouse gases Observing SATellite). We proposed an effective method for grasping the macroeconomic situation in real time. In addition, in the proposed method, the estimation accuracy of the economic model was improved by using fine-grained satellite information as a feature quantity.

著者

松波 夏樹 唐鎌 聡太郎

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.36, no.5, pp.G-L45_1-6, 2021-09-01 (Released:2021-09-01)

参考文献数

14

---

Towards close collaboration between a human and a large number of AI systems, we propose to design an AI agent with two technical elements. The first is the use of a modeling approach that enables us to know what AI agents are trying to do. The second is the use of a multi-agent consensus building algorithm. A good combination of these two, a human and a group of AI agents were put together as one team. In this paper, we explain a configuration using a Behavior Tree and a Contract Net Protocol as a concrete example. In addition, we propose a method of applying reinforcement learning in which the intentions of the AI agents can be easily grasped by a human. The effectiveness and feasibility of this approach were evaluated with teams in a simulated Tail Tag game. Matches were held with up to 29 AI agents and 1 person on one team and 30 people on the other team. The results indicate that our approach works almost evenly with human-human collaboration by sharing roles between a human and AI swarm.

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, 2021-09-01 (Released:2021-09-01)

参考文献数

11

---

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.

著者

本間 広樹 小町 守

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.B-L22_1-14, 2022-01-01 (Released:2022-01-01)

参考文献数

33

---

There are several problems in applying grammatical error correction (GEC) to a writing support system. One of them is the handling of sentences in the middle of the input. Till date, the performance of GEC for incomplete sentences is not well-known. Hence, we analyze the performance of GEC model for incomplete sentences. Another problem is the correction speed. When the speed is slow, the usability of the system is limited, and the user experience is degraded. Therefore, in this study, we also focus on the non-autoregressive (NAR) model, which is a widely studied fast decoding method. We perform GEC in Japanese with traditional autoregressive and recent NAR models and analyze their accuracy and speed. Furthermore, in this study, we construct a writing support system with a grammatical error correction function. Specifically, the trained NAR model is embedded in the back-end system. We confirm the system’s effectiveness by both objective and subjective evaluations.

著者

福馬 智生 鳥海 不二夫

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.5, pp.F-JC3_1-9, 2020-09-01 (Released:2020-09-01)

参考文献数

27

---

Latent factor models such as Matrix Factorization have become the default choice for recommender systems due to their performance and scalability. However, such algorithms have two disadvantages. First, these models suffer from data sparsity. Second, they fail to account for model uncertainty. In this paper, we exploit a meta learning strategy to address these problems. The key idea behind our method is to learn predictive distributions conditioned on context sets of arbitrary size of user/item interaction information. Our proposed framework has the advantages of being easy to implement and applicable to any existing latent factor models, providing uncertainty capabilities. We demonstrate the significant superior performance of our model over previous state-of-the-art methods, especially for sparse data in the top-N recommendation task.

著者

武田 惇史 鳥海 不二夫

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.36, no.6, pp.D-L36_1-12, 2021-11-01 (Released:2021-11-01)

参考文献数

21

---

One of the AI systems introduced into our society in recent years is a system that negotiates and collaborates with users by presenting and recommending information through dialogues with multiple users. In general, users have different cultures and values. Therefore, the system must be able to estimate those values and then adapt its behavior to the user. In this study, we focus on the "werewolf game" as a benchmark for this type of technology. The werewolf game is an imperfect information game in which the game proceeds through communication. A werewolf game is a team game and has both cooperative and adversarial characteristics. In werewolf games, it is important not to cause conflicts among allies due to differences in culture and way of thinking. In this study, we first create multiple agent groups with different cultures. Then, we show that there is no specific strong strategy, and that the optimal strategy is different for each group. Then, we build an agent that can estimate the culture of the strategy that players other than itself are following, and can act in such a way that it adapts itself to that culture, and conduct an evaluation based on the winning rate. The results show that the proposed agent is able to adapt to the group and increase its winning rate under certain limitations.

著者

佐藤 浩史 笠原 要 金杉 友子 天野 成昭

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.6, pp.502-510, 2004 (Released:2004-09-03)

参考文献数

26

被引用文献数

1 3

---

This paper proposes a new method for selecting fundamental vocabulary. We are presently constructing the Fundamental Vocabulary Knowledge-base of Japanese that contains integrated information on syntax, semantics and pragmatics, for the purposes of advanced natural language processing. This database mainly consists of a lexicon and a treebank: Lexeed (a Japanese Semantic Lexicon) and the Hinoki Treebank. Fundamental vocabulary selection is the first step in the construction of Lexeed. The vocabulary should include sufficient words to describe general concepts for self-expandability, and should not be prohibitively large to construct and maintain. There are two conventional methods for selecting fundamental vocabulary. The first is intuition-based selection by experts. This is the traditional method for making dictionaries. A weak point of this method is that the selection strongly depends on personal intuition. The second is corpus-based selection. This method is superior in objectivity to intuition-based selection, however, it is difficult to compile a sufficiently balanced corpora. We propose a psychologically-motivated selection method that adopts word familiarity as the selection criterion. Word familiarity is a rating that represents the familiarity of a word as a real number ranging from 1 (least familiar) to 7 (most familiar). We determined the word familiarity ratings statistically based on psychological experiments over 32 subjects. We selected about 30,000 words as the fundamental vocabulary, based on a minimum word familiarity threshold of 5. We also evaluated the vocabulary by comparing its word coverage with conventional intuition-based and corpus-based selection over dictionary definition sentences and novels, and demonstrated the superior coverage of our lexicon. Based on this, we conclude that the proposed method is superior to conventional methods for fundamental vocabulary selection.