Search

In this paper we introduce our haiku generator, which, in contrast to other systems, is not restricted to limited classic vocabulary sets and preserves a classic style without becoming too random and abstract because it performs a semantic integrity check using the Internet. Moreover, it is able to analyze blog entry input and, by using nouns and adjectives for web-mining, to stay on topic and still preserve kigo, traditional seasonal words used in Japanese poetry. The haiku generator utilizes grammar templates automatically generated from poems written by Japanese poets and a lexicon of 2,473 kigo words from an online haiku repository. In addition to generating haiku poems, it can output them vocally together with related sound effects and images retrieved from the WWW. Our experiments demonstrate that the proposed system generates high-quality haikus and that using contentrelated input and multimedia-rich output is effective for increasing users’ satisfaction. We have performed impression evaluation experiments and confirmed that our method is especially useful for generating haikus with higher depth and soundsharpness, which are two very important categories in professional evaluation of Japanese poetry. Next, haikus generated using the proposed method were evaluated by blog authors and blog readers and again, the proposed method outperformed the baseline. We also measured how the presence or absence of multimedia output influenced the evaluation. While using both vocal output and an image achieved higher scores than text alone, there were cases in which some combinations of effects were evaluated higher than all the effects used together. With our original approach to generating poetry, we wish to show the importance of new media and possibilities that are arising from the utilization of the “wisdom of (web-)crowds” in order to achieve higher standards for AI-generated art.

35th European Photovoltaic Solar Energy Conference and Exhibition; 6-11, Quantum dot (QD) solar cells have drawn much attention of research because of their capability of tuning the band gap and potential of realizing many novel concepts such as intermediate transitions. However, high nonradiative recombination rates in the quantum dot layer stands in the way of realizing high-efficiency QD solar cells. In this paper, efficiency potential of QD solar cells is discussed based on external radiative efficiency (ERE), open-circuit voltage loss and fill factor loss and non-radiative recombination loss via current-voltage characteristics in detailed balance model. Intrinsic loss of QD solar cells is substantially increased with increase in binding energy and volume density of QDs. External radiative efficiency of QD solar cells is decreased with increase in binding energy and volume density of QDs due to non-radiative recombination.

In this paper we introduce an approach for achieving a self that is able to simulate average ethical intuitions by retrieving knowledge about human behavior from the Internet resources. We show how applying text mining techniques could be useful for virtual and physical agents which base their knowledge on natural language. We discuss the importance of empathy and pros and cons of crowd experience based algorithm, then we introduce our thoughts on possibility of manufacturing agents for particular purposes as behavior analyzers or moral advisors which could refer to millions of different experiences had by people in various cultures. We think such systems could lead to selves that are capable to non-biased decisions morally superior to these of average human.

In this paper we present a survey on natural language corpora, with particular focus on corpora of large scale and those applicable to sentiment analysis. Natural language corpora are crucial for training various Software Engineering applications, from part-of-speech taggers and dependency parsers to dialog systems or sentiment analysis software. We compare several natural language corpora created for different languages, analyze their distinctive features and the amount of additional annotations provided by the developers of those corpora., ここに掲載した著作物の利用に関する注意 本著作物の著作権は日本ソフトウェア科学会 に帰属します．本著作物は著作権者である日本ソフトウェア科学会の許可のもとに掲載す るものです．ご利用に当たっては「著作権法」に従うことをお願いいたします． Notice for the use of this material: The copyright of this material is retained by the Japan Society for Software Science and Technology (JSSST). This material is published on this web site with the agreement of the JSSST. Please be complied with Copyright Law of Japan if any users wish to reproduce, make derivative work, distribute or make available to the public any part or whole thereof.

In this paper, we propose a language grounding method that relates verbs which imply body manipulation to motor angle patterns in a humanoid robot to make robots more entertaining. In established methods, verbs are represented by statistical models based on trajectories or motor patterns of a trajector. In our method we use a novel representation model that has six features including both trajector-reference point relationships and the trajector's trajectory. By using this model, some verbs which do not depend on a trajectory, e.g. "move the right hand close to the left hand." are represented more adequately. In our language grounding method a humanoid robot generates abstract verb meanings independent of context. As input it uses sets of a user input textual command and a motor pattern. The motor pattern is taught using direct physical feedback resembling playing with child. We implemented the algorithm in a humanoid robot and conducted a verb acquisition experiment. As a result, four problematic verbs, "place-on", "move-close-to", "move-away-from", and "touch-with" were acquired correctly.

This paper presents a novel approach to the estimationof user’s affective states in Human-ComputerInteraction. Most of the present approaches divideemotions strictly between positive or negative.However, recent discoveries in the field of EmotionalIntelligence show that emotions should berather perceived as context-sensitive engagementswith the world. This leads to a need to specifywhether the emotions conveyed in a conversationare appropriate for a situation they are expressedin. In the proposed method we use a system foraffect analysis on textual input to recognize usersemotions and a Web mining technique to verify thecontextual appropriateness of those emotions. Onthis basis a conversational agent can choose to eithersympathize with the user or help them managetheir emotions. Finally, the results of evaluationof the proposed method with two different conversationalagents are discussed, and perspectives forfurther development of the method are proposed.