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

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

定延 利之

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.30, no.1, pp.353-363, 2015

被引用文献数

1

---

In this paper, the author argues that mimetics are not morphological, syntactic, semantic phenomena by nature. Rather, they are a pragmatic behavior, spoken isolated from other sentential elements. This pragmatic behavior is characteristically performative (cf. Austin 1962). The performative characteristic of mimetics is utilized in the context of human play. This paper provides observations on this fact, and using the results of a questionnaire, it presents the possibility that machines may collaborate with humans by using mimetics in the manner of humans. More specifically, the following four points are examined: (i) The morphological, syntactic, semantic patterns often seen in mimetics, in which they are joined with other words in the sentence, such as an adjective noun, verb stem, or adverb, to illustrate or embellish descriptions more vividly, is not a characteristic of mimetics as they can be seen in other classifications of Japanese words, i.e. Yamato, Chinese, and foreign loan words, as well; (ii) In cases where mimetics are not joined with other words, they are spoken isolated from other sententil elements. This pragmatic behavior is hardly seen in other Yamato, Chinese, or foreign loan words and can be called a characteristic of mimetics. This pattern of verbal behavior in mimetics is performative (Austin 1962) on two points: first, if mimetics are not verbalized, the situation will not be apparent during the verbalization, and second, if mimetics are verbalized, this alone will make the situation apparent during the verbalization; (iii) This performative characteristic of mimetics is something that people utilize. One of the independent utterances of mimetics is used in the context of play, when acting as if some internal action had occurred in the speaker, although in fact no such action exists; (iv) There is the possibility that machines may collaborate with humans by using mimetics in the manner of humans. In other words, having machines use mimetics would evoke the context of play in the users; in that context, the machine would be able to act as if some internal action, as well as some physical action, had occurred, although in fact no such actions exist. This will cause the machine to give a cuter, more human, impression. A questionnaire survey conducted on 125 university students lends support to this idea.

著者

村上 晴美

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会全国大会論文集 (ISSN:27587347)

巻号頁・発行日

pp.226, 2002 (Released:2003-07-10)

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

Hung GUEI Ting-Han WEI I-Chen WU

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会全国大会論文集

巻号頁・発行日

pp.2J1E501, 2019 (Released:2019-06-01)

---

2048-like games are a family of single-player stochastic puzzle games, which consist of sliding numbered-tiles that combine to form tiles with larger numbers. Notable examples of games in this family include Threes!, 2048, and 2584. 2048-like games are highly suitable for educational purposes due to their simplicity and popularity. Numerous machine learning methods have been proposed for 2048, which provide a good opportunity for students to gain first-hand experience in applying these techniques. This paper summarizes the experience of using different 2048-like games, namely Threes! and 2584, as pedagogical tools for teaching reinforcement learning and computer game algorithms. With two classes of graduate level students, the average win rates for 2584 and Threes! reached 96.1% and 93.5%, respectively. The course designs were also well received by students, with 4.21/5 and 4.35/5 points from student feedbacks.

著者

Yuanzhi Ke Masafumi Hagiwara

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.33, no.4, pp.D-I23-1-8, 2018-07-01 (Released:2018-07-02)

参考文献数

25

被引用文献数

3

---

Although word embeddings are powerful, weakness on rare words, unknown words and issues of large vocabulary motivated people to explore alternative representations. While the character embeddings have been successful for alphabetical languages, Japanese is difficult to be processed at the character level as well because of the large vocabulary of kanji, written in the Chinese characters. In order to achieve fewer parameters and better generalization on infrequent words and characters, we proposed a model that encodes Japanese texts from the radical-level representation, inspired by the experimental findings in the field of psycholinguistics. The proposed model is comprised of a convolutional local encoder and a recurrent global encoder. For the convolutional encoder, we propose a novel combination of two kinds of convolutional filters of different strides in one layer to extract information from the different levels. We compare the proposed radical-level model with the state-of-the-art word and character embedding-based models in the sentiment classification task. The proposed model outperformed the state-of-the-art models for the randomly sampled texts and the texts that contain unknown characters, with 91% and 12% fewer parameters than the word embedding-based and character embedding-based models, respectively. Especially for the test sets of unknown characters, the results by the proposed model were 4.01% and 2.38% above the word embedding-based and character embedding-based baselines, respectively. The proposed model is powerful with cheaper computational and storage cost, can be used for devices with limited storage and to process texts of rare characters.

著者

恒川 充 岡 夏樹 荒木 雅弘 新谷 元司 吉川 昌孝 谷川 武

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会全国大会論文集

巻号頁・発行日

pp.4D3E205, 2019 (Released:2019-06-01)

---

本研究では,定期的な健診データを用いて生活習慣病の発症を予測する手法を提案する.レセプトデータを精査して疾病の発症を特定し,それらを教師あり学習のための正例として使用した.クラスバランスが不均衡なデータであるという問題に対処するために,アンダーサンプリングとバギングのアプローチを採用した.がん以外の生活習慣病が1年以内に発症するかどうかを予測することを目的とした.提案手法のprecisionとrecallはそれぞれ0.32と0.89であった.各検査項目に閾値を設定し,それらの論理和をとるというベースライン手法と比較して,提案手法はrecallを維持しながらより高いprecisionが得られることが分かった.これは,重症化しそうな対象者の見落としを増やすことなく,保健指導の対象者数を抑えることができるという点で意義がある.

著者

熊本 忠彦 太田 公子

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.21, pp.310-318, 2006-11-01

参考文献数

12

被引用文献数

7 5

---

Impression-based music retrieval helps users in finding musical pieces that suit their preferences, feelings, or mental states from the huge volume of a music database. We have therefore developed an impression-based music retrieval system that enables this. Users are asked to select one or more pairs of impression words from the multiple pairs presented by the system and estimate each of the selected pairs on a seven-step scale in order to input their impressions into the system. For instance, if they want to locate musical pieces that will create a happy impression, they should check the radio button ``Happy'' in the impression scale, ``Very happy -- Happy -- A little happy -- Neutral -- A little sad -- Sad -- Very sad,'' where a pair of impression words with a seven-step scale is called an ``impression scale'' in this paper. The system would measure the distance between the impressions of every musical piece in a user-specified music database and the impressions inputted by the user, and determine candidate musical pieces to be presented as retrieval results. In this paper, we define the form of vectors that numerically express impressions of musical pieces, and propose a method of generating such a vector from a musical piece. The most significant attribute of this method is that it uses n-gram statistics of information on pitch, strength, and length of every tone in that musical piece as features extracted from it. We also present the results of evaluating the performance of the system.

著者

水谷 哲也 田中 崇之 五十嵐 滋

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会全国大会論文集

巻号頁・発行日

pp.148-148, 2001 (Released:2003-07-10)

著者

和泉 潔 後藤 卓 松井 藤五郎

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.25, no.3, pp.383-387, 2010

被引用文献数

5 7

---

In this study, we proposed a new text-mining methods for long-term market analysis. Using our method, we analyzed monthly price data of financial markets; Japanese government bond market, Japanese stock market, and the yen-dollar market. First we extracted feature vectors from monthly reports of Bank of Japan. Then, trends of each market were estimated by regression analysis using the feature vectors. As a result, determination coefficients were over 75%, and market trends were explained well by the information that was extracted from textual data. We compared the predictive power of our method among the markets. As a result, the method could estimate JGB market best and the stock market is the second.

著者

伊藤 寛隆 田中 敏光 杉江 昇

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.161-164, 2003-11-01

参考文献数

9

---

In order to realize advanced man-machine interfaces, it is desired to develop a system that can infer the mental state of human users and then return appropriate responses. As the first step toward the above goal, we developed a system capable of inferring human tactics in a simple game played between the system and a human. We present a machine learning system that plays a color expectation game. The system infers the tactics of the opponent, and then decides the action based on the result. We employed a modified version of classifier system like XCS in order to design the system. In addition, three methods are proposed in order to accelerate the learning rate. They are a masking method, an iterative method, and tactics templates. The results of computer experiments confirmed that the proposed methods effectively accelerate the machine learning. The masking method and the iterative method are effective to a simple strategy that considers only a part of past information. However, study speed of these methods is not enough for the tactics that refers to a lot of past information. For the case, the tactics template was able to settle the study rapidly when the tactics is identified.

著者

飯塚 修平 松尾 豊

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.29, no.5, pp.460-468, 2014

被引用文献数

1

---

Webpage optimization is an experimental method to make continuous improvements on websites based on users behavior. This method can be implemented easily but has a drawback that small websites take long time to gather enough data to evaluate the ideas. Although many optimization methods are proposed and conducted so far, theres no mathematical model of this problem. We propose Webpage Optimization Problem and organize existing webpage optimization methods. Combining these methods, we also propose a new webpage optimization method that performs well no matter how many people get to the website. We evaluate the proposal method by simulation experiments and introducing the optimization program to both large and small websites. The results show that our proposal method outperforms existing methods at any size of websites. Webpage Optimization Problem is a framework to create new webpage optimization methods.

著者

佐藤 晃矢 岡 瑞起 橋本 康弘 加藤 和彦

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.30, no.5, pp.667-674, 2015

---

Social Tagging System (STS) which is one of the content management techniques is widely adopted in the online content sharing service. Using STS, users can give any strings (tags) to contents as annotations. It is important to know the usage of tag statistics for accomplishing an effective database design and the information navigation. The frequency of tag usage as well as their dynamics are similar to the ones found in the natural language. It is possible to reproduce the branching process of the tag dynamics using a classical model called Yule-Simon process. Another characteristic aspect of tags is the tag co-occurrence generated from the simultaneous use of tags. Using the tag co-occurrence, STS is able to reconstitute the hierarchy of tags, and recommend the tag which is probably used next. However, Yule-Simon process does not consider the tag co-occurrence and thus how the tag co-occurrence is generated from the model like Yule-Simon has not been addressed yet. In this paper, we propose to expand the Yule-Simon process to model the tag co-occurrence. From the point of view of network hierarchy, we confirm the similarity in the structure of the tag co-occurrence with the empirical data obtained from a social network service called 'RoomClip'. The present result suggested that this simple model like extended Yule-Simon process generates the tag co-occurrence feature.

著者

松原 仁 田中 久美子 Frank Ian 田所 諭

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.17, pp.177-180, 2002-11-01

被引用文献数

4 2

---

We address the problem of information flow in disaster relief scenarios by presenting an architecture for generating natural language dialogue between large numbers of agents. This architecture is the first step towards real-time support systems for relief workers and their controllers. Our work demonstrates how natural generation techniques from the MIKE commentary system for RoboCup soccer can be carried over to that of RoboCup Rescue. Thanks to this background, the initial product of our research is a system that explains a RoboCup Rescue simulation not to the agents in the domain themselves but to a watching audience. This "commentary" is produced by recreating the actual dialogues most likely be occurring in the domain: walkie-talkie-conversations.

著者

森田 千絵

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会全国大会論文集

巻号頁・発行日

pp.30, 2002 (Released:2003-07-10)

著者

山縣 友紀 古崎 晃司 今井 健 大江 和彦 溝口 理一郎

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

2016

---

Linked Data is a promising technology for knowledge integration on the web. Many research groups have developed ontologies and terminologies, and recently, they have published a wide variety of Linked Data in the biomedical domain. We have systematized an ontology of abnormal states in the definition of diseases. For effective use of existing biomedical data, one of the difficulties is a conceptual discrepancy rather than a superficial one since data are heterogeneous. This article focuses on knowledge integration with Linked Data in terms of abnormal states. First, we discuss ontological issues of reusing and integrating knowledge of abnormal states in existing biomedical resources. Next, we introduce our ontology of abnormal states. By using our ontology and making explicit the meaning of each concept, we show a solution for the integration. Then, applying a Linked Data technology, we introduce a prototype system to link our ontology as a hub of existing resources across species. In cooperation with disease ontology, we demonstrate finding commonality of causal relationships of abnormal states between diseases across clinical departments. Our approach will bring benefits to fill the gap between basic research and clinical medicine, and contribute to disease knowledge integration of good practice.

著者

芦川 将之 川村 隆浩 大須賀 昭彦

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.29, no.6, pp.503-515, 2014

被引用文献数

2

---

Open Crowdsourcing platforms like Amazon Mechanical Turk provide an attractive solution for process of high volume tasks with low costs. However problems of quality control is still of major interest. In this paper, we design a private crowdsourcing system, where we can devise methods for the quality control. For the quality control, we introduce four worker selection methods, each of which we call preprocessing filtering, real-time filtering, post processing filtering, and guess processing filtering. These methods include a novel approach, which utilizes a collaborative filtering technique in addition to a basic approach of initial training or gold standard data. For an use case, we have built a very large dictionary, which is necessary for Large Vocabulary Continuous Speech Recognition and Text-to-Speech. We show how the system yields high quality results for some difficult tasks of word extraction, part-of-speech tagging, and pronunciation prediction to build a large dictionary.

著者

前野 義晴 大澤 幸生

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.389-396, 2007-11-01

被引用文献数

4 3

---

This paper addresses a new problem to infer an invisible fixer in an organization from communication (node discovery problem). Human-interactive annealing together with crystallization algorithm aims at inventing scenarios from the gap between prior understanding and observation. Four functions for ranking the relevance of the portion of observation, and two types of communication strength within an organization are studied. In the experiment, information relevant to identify an invisible fixer in an online decision-making environment is successfully retrieved.

著者

岩爪 道昭 小林 一郎 伊藤 紀子 高橋 祐介 藤城 浩子 菅野 道夫

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.17, pp.181-185, 2002-11-01

被引用文献数

4 4

---

The aim of this study is to provide all people, from small children to aged persons, with a computational environment for everyday language communication. In order to achieve this, we propose a framework for a language-based operating system. In this paper, we explain our approach to dealing with the meaning of language, the architecture of the language operating system and its components. In particular, we describe the notion of language protocol and its resource representation (i.e., semiotic base), compared to the other protocols and their resource representations. We argue that by processing meaning of language rather than processing information, we attempt to provide a more human-like computer system and an intelligent computational environment to all people.