著者

山元 翔 松林 達史

出版者

一般社団法人 人工知能学会

雑誌

人工知能 (ISSN:21882266)

巻号頁・発行日

vol.38, no.3, pp.437-439, 2023-05-01 (Released:2023-05-01)

著者

相馬 輔

出版者

一般社団法人 人工知能学会

雑誌

人工知能 (ISSN:21882266)

巻号頁・発行日

vol.37, no.2, pp.234-236, 2022-03-01 (Released:2022-03-01)

著者

小宮山 純平

出版者

一般社団法人 人工知能学会

雑誌

人工知能 (ISSN:21882266)

巻号頁・発行日

vol.36, no.5, pp.651-653, 2021-09-01 (Released:2021-09-01)

著者

小林 潤平 関口 隆 新堀 英二 川嶋 稔夫

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.32, no.2, pp.A-AI30_1-24, 2017-03-01 (Released:2017-03-01)

参考文献数

61

被引用文献数

3

---

We propose bunsetsu-based layouts to improve the efficiency of eye movements in reading Japanese text. When reading text, people tend to direct their gaze toward the center of a word. This is called the optimal viewing position. The optimal viewing position results in the shortest gaze durations and fewest re-fixations. In the case of Japanese text, the eyes tend to fixate on each characteristic Japanese linguistic unit (bunsetsu). An electronic Japanese text reader that facilitates accurate control of eye movements to bunsetsu segments could increase the reading rateand result in more efficient eye movements. In this study, we develop new techniques to decrease inefficient eye movements when reading Japanese text. In Experiment I, we investigate the effectiveness of the layout with bunsetsu-based line breaking. A bunsetsubased linefeed layout breaks a line between bunsetsu segments, i.e., splitting a bunsetsu segment is prohibited. The reading speed for the bunsetsu-based linefeed layout was faster compared to the conventional text layout with line lengths of 5–40 characters per line. The improvements in reading speed were likely due to the optimization of eye movements near the edge of a line. In the case of 5–11 characters per line, the improvements in reading speed were likely due to an increase in the number of lines that can be recognized by a single fixation. These results indicate that the bunsetsu-based linefeed layout is an effective technique to improve reading efficiency. In Experiment II, we develop a new micro-vibration text reader with bunsetsu-based segmentation. The new reader vibrates each bunsetsu segment in a different phase to enhance boundary information for eye guidance. The reading speed for the micro-vibration text was approximately 7%–12% faster compared to the stable text with line lengths of approximately 11–29 characters per line. The improvements in reading speed were likely due to a reduction in re-fixations within a bunsetsu segment and an increase in the number of lines that can be recognized by a single fixation without horizontal saccades. Moreover, 76% of the participants did not experience illegibility or incongruousness with the micro-vibration text reader. These results indicate that micro-vibration is an effective technique to improve the efficiency of reading text with line lengths of 11–29 characters per line without an increase in cognitive load or a decrease in comprehension. In Experiment III, we develop a new stepwise incremental indent layout with bunsetsu-based segmentation and a vertical scrolling operation. The reading speed obtained by the proposed layout of 4.4 characters per line was comparable to the fixed-line length layout of 29 characters per line. This improvement is primarily achieved by a reduction in the number of fixations. Moreover, 85% of the participants did not experience illegibility or incongruousness with the stepwise incremental indent layout reading. These results indicate that this layout is an effective technique to improve the efficiency of reading text with line lengths of 5 characters per line without an increase in cognitive load or a decrease in comprehension. These experimental results indicate that the Japanese electronic text reader with these proposed techniques can improve the reading speed of text with line lengths of 5–40 characters per line without an increase in cognitive load or decrease in comprehension.

著者

榊 剛史 鳥海 不二夫

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会全国大会論文集 第32回 (2018)

巻号頁・発行日

pp.2C201, 2018 (Released:2018-07-30)

---

フェイクニュースや炎上,エコチェンバー現象など,近年は個人による情報発信における負の側面が注目されている.我々は,それらの現象を引き起こす原因の一つとして,ソーシャルポルノという仮説を提案する.ソーシャルポルノとは,「特定のコミュニティに属するユーザが、脊髄反射的に拡散・共有してしまいたくなる情報」を意味する. 本論文では,ソーシャルポルノの観測を行う前段階として,ユーザ反応時間という尺度を定義し,いくつかのツイートについて,ユーザ反応時間分布の違いを考察した.結果として,特定のコミュニティのユーザが拡散する投稿とランダム抽出した投稿には,ユーザ反応時間の分布に違いが生じる可能性が示唆された.

著者

金井 良太 藤澤 逸平 玉井 信也 眞方 篤史 安本 雅啓

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会第二種研究会資料 (ISSN:24365556)

巻号頁・発行日

vol.2019, no.AGI-013, pp.11, 2019-11-22 (Released:2021-09-16)

---

In this paper, we propose a hypothesis that consciousness has evolved to serve as a platform for general intelligence. This idea stems from considerations of potential biological functions of consciousness. Here we define general intelligence as the ability to apply knowledge and models acquired from past experiences to generate solutions to novel problems. Based on this definition, we propose three possible ways to establish general intelligence under existing methodologies for constructing AI systems, namely solution by simulation, solution by combination and solution by generation. Then, we relate those solutions to putative functions of consciousness put forward, respectively, by the information generation theory, the global workspace theory, and a form of higher order theory where qualia are regarded as meta-representations. Based on these insights, We propose that consciousness integrates a group of specialized generative/forward models and forms a complex in which combinations of those models are flexibly formed and that qualia are meta-representations of first-order mappings which endow an agent with the ability to choose which maps to use to solve novel problems. These functions can be implemented as an "artificial consciousness". Such systems can generate policies based on a small number of trial and error for solving novel problems. Finally, we propose possible directions for future research into artificial consciousness and artificial general intelligence.

著者

坂本 圭隆

出版者

一般社団法人 人工知能学会

雑誌

人工知能 (ISSN:21882266)

巻号頁・発行日

vol.36, no.4, pp.532-534, 2021-07-01 (Released:2021-07-01)

著者

長尾 真

出版者

一般社団法人 人工知能学会

雑誌

人工知能 (ISSN:21882266)

巻号頁・発行日

vol.2, no.3, pp.259, 1987-09-01 (Released:2020-09-29)

著者

石川 葉子 水上 雅博 吉野 幸一郎 Sakti Sakriani 鈴木 優 中村 哲

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.33, no.1, pp.DSH-B_1-9, 2018-01-01 (Released:2018-01-31)

参考文献数

20

被引用文献数

1

---

Using emotional expressions in a conversation is an efficient way to convey one’s thoughts. Emotional expressions of the persuader have a strong impact to the recipient’s attitude in a negotiation. Studies for a persuasive dialog system, which tries to lead users to the system’s specific goals, show that incorporating users’ emotional factors can enhance the system to persuade users. However, in a human-human negotiation, the persuader can have better outcomes not only through considering the emotion of the other person but also through expressing his or her own emotions. In this paper, we propose an example-based persuasive dialog system with expressive emotion capability. The proposed dialog system is trained by newly collected corpus with statistical learning. Emotional states and the user’s acceptance rate of the persuasion are annotated. Experimental results through crowdsourcing suggested that the system using emotional expressions has a potential to persuade some users who prefer to be used emotional expressions, effectively.

著者

平田 佐智子 中村 聡史 小松 孝徳 秋田 喜美

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.274-281, 2015-01-06 (Released:2015-01-06)

参考文献数

15

---

Japanese “onomatopoeic” words (also called mimetics and ideophones) are more frequent in spoken discourse, especially in informal daily conversations, than in writing. It is a common belief that onomatopoeia is particularly frequent in some areas, such as the Kinki region. To examine the plausibility of this folk dialectology, we investigated the frequency of onomatopoeia in the Minutes of the Diet as a corpus of spoken Japanese. We examined whether there is really a difference in the use of onomatopoeia among the eleven major regions of Japan. We analyzed the conversation data (limited to the last two decades) according to the hometowns of the speakers. The results revealed that there is no cross-regional difference in the overall frequency of onomatopoeia and non-onomatopoeic adverbs. However, a particular morphological type of onomatopoeia?i.e., “emphatic” onomatopoeia, such as hakkiri ‘clearly’?did show a regional variation in frequency. The results suggest that different types of onomatopoeia have different functions. The present study introduced a “macro-viewpoint” method that is based on a large-scale database. Further investigations into the functional aspect of onomatopoeia will also benefit from a dialectological method that adopts a “micro-viewpoint” on the detailed descriptions of a small number of speakers from each region. We hope that the present quantitative approach to the sociolinguistics of onomatopoeia will offer a new perspective on dialectology and on the effective utilization of onomatopoeia in the field of information science.

著者

辰巳 格

出版者

一般社団法人 人工知能学会

雑誌

人工知能 (ISSN:21882266)

巻号頁・発行日

vol.21, no.4, pp.i_490-498, 2006-07-01 (Released:2020-09-29)

著者

小坂 直輝 小林 哲則 林 良彦

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会全国大会論文集 第34回 (2020)

巻号頁・発行日

pp.3Rin477, 2020 (Released:2020-06-19)

---

近年,インターネット上で個人が小説を投稿できる,小説投稿サイトが多数開設され,数多くの作品が投稿されている.こうした作品はweb小説等と呼ばれ,これらの中には商業用に書籍化・映像化される作品も存在している.一方でこれらweb小説に関して,その作品数の多さから読者が好みの作品を探すのが難しいという問題や,人気の作品や最新の作品といった限られた少数の作品に大多数の読者が集中し隠れた良作が出来てしまうという問題がある.本研究の目的は,上記問題点を解決し,ユーザが作品を探すのを助ける推薦システムを実現することである.具体的には,作品の本文とジャンルやキーワードといった付属情報から,作品の類似度や質を推定することで,読者の評価情報が無い作品の推薦や,ユーザによる推薦基準の操作が可能な推薦システムを試作し評価を行った.結果として,作品の類似度や質を一定の精度で予測でき,試作したシステムが隠れた良作を発掘するのに有用であることが示唆された.

著者

山崎 天 坂田 亘 川本 稔己 小林 滉河 Nguyen Tung 上村 卓史 中町 礼文 李 聖哲 佐藤 敏紀

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会研究会資料 言語・音声理解と対話処理研究会 93回 (2021/11) (ISSN:09185682)

巻号頁・発行日

pp.113-118, 2021 (Released:2021-11-20)

---

本稿では、対話システムライブコンペティション4のオープントラックに提出した対話システムについて述べる。本システムはTransformerをベースとした言語モデルの「HyperCLOVA」を用い、ユーザの発話に応じて選択するFew-Shotプロンプトを利用して応答候補の生成を行う。プロンプトは4種類あり、一般的な応答生成、知識応答生成、ペルソナ一貫性を考慮した応答生成、短文抑制のための応答生成を目的としたものをそれぞれ用意し、組み合わせて利用する。後に、不適切な発話を除去するフィルタリングを行うことで、最終的な出力を得るシステムとなっている。予選の結果では1位を獲得し、大規模言語モデルが雑談応答生成に有効であることを示したが、攻撃的な応答生成をはじめとしたいくつかの課題が顕在化した。本稿では、大規模言語モデルを用いた雑談応用における現存の課題や今後の方向性を議論する。

著者

成田 悠輔 矢田 紘平

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会全国大会論文集 第34回 (2020)

巻号頁・発行日

pp.2I5GS205, 2020 (Released:2020-06-19)

---

機械学習を利用した意思決定を行う際、過去に使われたことのない新しい意思決定アルゴリズムの性能を予測したい場面が多々ある。私たちは、過去に使われたアルゴリズムの下で蓄積されたデータを用い、新たなアルゴリズムの評価を行う方法を提案する。この方法は次の観察に基づく。機械学習を利用して意思決定を行う場合、そこから生成されるデータには、選択がランダムに行われるA/Bテスト的状況が含まれるという観察だ。例えば、多くの確率的な強化学習・バンディットアルゴリズムは選択をランダムに行うため、ほとんどA/Bテストそのものである。また、教師付き学習で予測された何らかのスコアがある基準値を上回るかどうかで選択を変えるアルゴリズムを考える。この場合、基準値付近では、ほぼ同じ状況であるにもかかわらず異なった選択が行われるため、同じくA/Bテスト的状況とみなせる。私たちはこの観察を一般の機械学習アルゴリズムについて定式化し、アルゴリズムが自然に生成したデータを用いてアルゴリズムを改善する手法を提示する。この手法が使える場面は、ウェブ広告配信から裁判の判決や金融機関の審査、そしてデータ駆動教育・医療まで多岐にわたる。

著者

久保 健治 中川 慧 水上 大樹 Acharya Dipesh

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会第二種研究会資料 (ISSN:24365556)

巻号頁・発行日

vol.2022, no.FIN-029, pp.23-27, 2022-10-08 (Released:2022-10-01)

---

暗号資産販売所は、ビッド・アスク価格を提示し、顧客から暗号資産の注文を受け付ける相対取引サービスであり、暗号資産市場に流動性を供給している。顧客からの注文によって販売所の暗号資産の在庫は変化し、一方で、在庫は常に価格変動リスクに晒される。このため、適切な在庫管理が必要になる。同じ相対取引サービスである FX ディーラーの在庫管理問題については、確率制御に基づいた最適流動化戦略が提案されている。ただし、暗号資産市場は FX 市場と比べ、流動性が低く、ボラティリティが大きい。更に、暗号資産販売所においては顧客から注文に大きな偏りがみられる。そのため、暗号資産販売所における在庫管理問題を解決するためには、暗号資産市場に特有の性質を考慮して、最適流動化戦略を構築する必要がある。そこで、本研究では暗号資産販売所に対する在庫管理問題を定義し、確率制御に基づき最適流動化戦略を提案する。また、モデルパラメータを bitFlyer の公開データを用いて推定し、数値計算により、最適流動化戦略を得た。得られた結果から、注文頻度の偏りが最適流動化戦略に影響を与えることを示した。また、単純な流動化戦略と比較することで、提案手法の有効性も確認した。本研究は暗号資産販売所における最適流動化戦略という新たな領域を開拓するものになるであろう。

著者

稲本 万里子 加藤 拓也 小長谷 明彦

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.36, no.6, pp.F-L12_1-16, 2021-11-01 (Released:2021-11-01)

参考文献数

14

---

”Phantom Genji Scrolls ”are one of the most debatable artifacts whose painter school is still unknown in the history of art. In this study, the authors have reached a conclusion that the Phantom Genji Scrolls would have been painted by the painters who studied Kyoto-Kano and Tosa painter schools but not Edo-Kano painter school.As a learning data set, more than 1500 face images are extracted from well-known the Tale of Genji pictures painted from Heian (12 Century) to Edo (17 Century) periods whose painter schools are all established in the history of art. The face images are written in typical old painting style so called“line-eye and hook nose (hikime-kagihana)” which often represents the characteristics of the painter schools.The authors not only identified the painter school of the Phantom Genji Scrolls but also discovered the inconsistency in Iwasa painter school by means of artifact-based painter school learning model. The t-SNE scatter plots clearly indicated that the 266 face images extracted from the Phantom Genji Scrolls were surrounded by the Kyoto- Kano painter school learning data sets. It should be also noted that the 266 face images were far from the learning data set of Ujinobu Kano, one of the typical Edo-Kano painter. Interestingly, the Phantom Genji Scrolls and Ujinobu Kano were intercepted by Mitsuyoshi Tosa, one of the typical Tosa painter in scatter plot. This suggests that the painters of the Phantom Genji Scrolls may have been affected by both Kyoto-Kano and Tosa painter schools, instead of Edo-Kano painter school.As for the Iwasa painter school, the authors came across strange behavior that the artifacts of Katsutomo Iwasa were identified as the Tosa painter school, even if the validation data of Katsutomo Iwasa were all included in the learning data set of Iwasa painter school, mostly constituted by Katsutomo Iwasa (244 face images). After careful observation and discussion, the authors have concluded that Matabei Iwasa and Kastutomo Iwasa may be too different to be categorized into the same Iwasa painter school with regards to face characteristics.

著者

吉田 光男

出版者

一般社団法人 人工知能学会

雑誌

人工知能 (ISSN:21882266)

巻号頁・発行日

vol.35, no.5, pp.644-653, 2020-09-01 (Released:2020-11-02)

著者

清水 祐一郎 土斐崎 龍一 坂本 真樹

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.29, no.1, pp.41-52, 2014-01-05 (Released:2014-01-07)

参考文献数

23

被引用文献数

13 6

---

In Japanese, onomatopoeia (i.e., imitative or mimetic words) is frequently used in daily life conversation to express one's intuitive and sensitive feelings. Many onomatopoeic expressions are very similar to each other and their meanings seem to be vague and ambiguous so that it is hard to catch minute semantic differences among onomatopoeic expressions. However, we use onomatopoeia, even novel onomatopoeia, to express our subjective, intuitive and sensitive feelings in daily language use. Therefore, estimating information conveyed by onomatopoeia is inevitable in constructing a human-like intelligent communication system. In this study, we propose a system to estimate information conveyed by onomatopoeia based on Japanese sound symbolism. The existence of synesthetic associations between sounds and sensory experiences (sound symbolism) has been demonstrated over the decades. It is also known that the sensory-sound correspondence can be found not only in words referring to visual shapes, but also in those referring to tactile sensations. So our system quantifies images of inputted onomatopoeia using 43 adjective pair scales related to visual and tactile sensations. Our method hypothesizes that the impression created by an onomatopoeic expression could be predicted by the phonological characteristics of its constituent phonemes. To collect phonemic image data, we conducted a psychological experiment where 78 participants were asked to evaluate the impressions of 312 onomatopoeic expressions, which cover all kinds of Japanese phonemes, against 43 pairs of adjectives in seven-points SD scales. We applied the phonemic image data to our model, and calculated the impression values of each phoneme by making use of a mathematical quantification theory class I. This system estimates rich information conveyed by not only conventional but also newly created onomatopoeic expressions and differentiates among a variety of onomatopoeic expressions, which are frequently similar to each other. We conducted another psychological experiment in order to confirm the effectiveness of our system. Results showed that our system succeeded in evaluating information conveyed by onomatopoeia.

著者

高瀬 翔 坂本 陸 大北 剛

出版者

一般社団法人 人工知能学会

雑誌

人工知能 (ISSN:21882266)

巻号頁・発行日

vol.36, no.4, pp.527-531, 2021-07-01 (Released:2021-07-01)

著者

田村 浩一郎 松尾 豊

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.35, no.6, pp.A-K61_1-11, 2020-11-01 (Released:2020-11-01)

参考文献数

32

被引用文献数

1

---

The data of social media has received much attention to observe and predict real-world events. For example, It is used to predict financial markets, products demand, and voter turnout. While these works regards social media as a sensor of real world, as social media become more popular, it become more natural to think social media significantly effects on real worlds events. The canonical example might be cryptocurrencies, where supply and demand are more susceptible to investor sentiment and therefore interactions within social media cause significant effects on the price of them. On the hypothesis that social media actuate real-world events, we propose a neural network based model to predict the price fluctuations of financial assets, including cryptocurrencies. We model the effect of social media which cannot be directly observed, using an end-to-end neural network, Recurrent Neural Network. By simulating the effect within the social media, we show that the method that models the effect of social media on financial markets can observe and predict the price fluctuations of cryptocurrencies more precisely and stably. By analyzing the model, we suggest that networks within social media can be influential relationships throughout time, even if they are not directly connected, and that the intensity of the influence from social media on financial markets varies depending on the nature of the financial assets.