著者

勝見 久央 吉野 幸一郎 平岡 拓也 秋元 康佑 山本 風人 本浦 庄太 定政 邦彦 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.35, no.1, pp.DSI-D_1-12, 2020-01-01 (Released:2020-01-01)

参考文献数

28

被引用文献数

1

---

Argumentation-based dialogue systems, which can handle and exchange arguments through dialogue, have been widely researched. It is required that these systems have sufficient supporting information to argue their claims rationally; however, the systems do not often have enough information in realistic situations. One way to fill in the gap is acquiring such missing information from dialogue partners (information-seeking dialogue). Existing informationseeking dialogue systems were based on handcrafted dialogue strategies that exhaustively examine missing information. However, these strategies were not specialized in collecting information for constructing rational arguments. Moreover, the number of system’s inquiry candidates grows in accordance with the size of the argument set that the system deal with. In this paper, we formalize the process of information-seeking dialogue as Markov decision processes (MDPs) and apply deep reinforcement learning (DRL) for automatic optimization of a dialogue strategy. By utilizing DRL, our dialogue strategy can successfully minimize objective functions: the number of turns it takes for our system to collect necessary information in a dialogue. We also proposed another dialogue strategy optimization based on the knowledge existence. We modeled the knowledge of the dialogue partner by using Bernoulli mixture distribution. We conducted dialogue experiments using two datasets from different domains of argumentative dialogue. Experimental results show that the proposed dialogue strategy optimization outperformed existing heuristic dialogue strategies.

著者

松林 達史 幸島 匡宏 林 亜紀 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.6, pp.713-720, 2015-11-01 (Released:2015-10-27)

参考文献数

22

被引用文献数

6 7

---

In marketing science field, modeling of purchase behavior and analysis of brand choice are important research tasks. This paper presents a method that enables such analysis by time-series pattern extraction based on Non-negative Tensor Factorization (NTF). The development of the scanning devices and electronic payments (e.g. online shopping, mobile-phone wallet and electronic money) has led to the accumulation of more detailed POS data including the information about purchase shop, amount of payment, time, location and so on and it brings possibilities for more deep understanding of purchasing behaviors. On the other hand, due to the increase of the number of attributes, it is still difficult to effectively and efficiently handle large feature quantities. In this paper, we consider feature quantities as high-order tensor. Then, using NTF for simultaneous decomposition of multiple attributes, we show analytic effectiveness of pattern factorization for real Beer Item/Brand purchase data. By applying NTF considering three axes: USER-ID × TIME-STAMP × ITEM-ID,we find several temporal tendencies depending on the season.In addition, by focusing on the purchase-pattern correlations between beer items and brands, we find that the tendencies of brand choice strategies appear on the graph drawing results.

著者

宮崎 千明 平野 徹 東中 竜一郎 牧野 俊朗 松尾 義博 佐藤 理史

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

pp.DSF-515, (Released:2015-12-15)

参考文献数

13

---

Characterizing dialogue system utterances is important in making human-computer interaction systems more friendly and human-like. A method is described for achieving this by converting functional expressions according to their generation probabilities, which are calculated for specific characters. Experimental results show that the method can add characteristics of the target profiles (i.e., gender, age and closeness with a conversation partner) to dialogue system utterances and in so doing can generate a large variety of linguistic expressions.

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.30, no.2, pp.479-484, 2015-03-01 (Released:2015-02-19)

参考文献数

14

被引用文献数

2 1

---

We propose a new Japanese electronic text format with phrase-based line breaking for tablet computer to improve reading speed. The new text format prohibits splitting of a phrase and breaks a line between phrases. We measured reading speeds and eye movements using both the new text format and a conventional text format. Reading speeds for the new text formats are faster compared to the conventional text formats at all line lengths tested. The enhancement of reading speed in the new text format seems to be caused by the optimization of eye movements at the beginning of a long-length line, and the increase of short-length lines that can be recognized by a single fixation without horizontal saccade.

著者

The Tung Nguyen Koichiro Yoshino Sakriani Sakti Satoshi Nakamura

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.35, no.1, pp.DSI-C_1-12, 2020-01-01 (Released:2020-01-01)

参考文献数

24

被引用文献数

2

---

In the past few years, there has been an increasing number of works on negotiation dialog. These studies mainly focus on situations where interlocutors work cooperatively to agree on a mutual objective that can fulfill each of their own requirements. However, in real-life negotiation, such situations do not happen all the time, and participants can tell lies to gain an advantage. In this research, we propose a negotiation dialog management system that detects when a user is lying and a dialog behavior for how the system should react when faced with a lie. We design our system for a living habits consultation scenario, where the system tries to persuade users to adopt healthy living habits. We show that we can use the partially observable Markov decision process (POMDP) to model this conversation and use reinforcement learning to train the system’s policy. Our experimental results demonstrate that the dialog manager considering deceptive states outperformed a dialog manager without this consideration in terms of the accuracy of action selection, and improved the true success rate of the negotiation in the healthcare consultation domain.

著者

山縣 友紀 五十嵐 芳暢 中津 則之 堀本 勝久 福井 一彦 植沢 芳広 山田 弘

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.34, no.2, pp.D-I81_1-18, 2019-03-01 (Released:2019-03-01)

参考文献数

40

被引用文献数

2

---

In drug development, Drug-Induced Liver Injury (DILI) is a significant cause of discontinuation of development, and safety evaluation and management technology at early development stage are highly required. In recent years, toxicity prediction by in silico analysis is expected, and the machine learning research using omics data has attracted attention. However, the lack of explanation of machine learning is a problem. In order to make an appropriate safety assessment, it is necessary to clarify the mechanism of the toxicity (toxic course). In this study, we focus on the toxic course and propose an ontological model of the liver toxicity, which systematizes toxicity knowledge based on a consistent viewpoint. In application research, we introduce a prototype of a knowledge system for supporting toxicity mechanism interpretation. Based on the ontology, this system provides information flexibly according to the user's purpose by using semantic technologies. The system provides a graph visualization function in which nodes correspond to concepts and edges correspond to interactions between concepts. In such a visualization function, a toxic course map shows causal relationships of the toxic process. We illustrate examples of application to safety assessment and management by combining ontological and data-driven methodologies. Our ontological engineering solution contributes to converting from data to higher-order knowledge and making the data explainable in both human and computer understandable manner. We believe that our approach can be expected as a fundamental technology and will be useful for a wide range of applications in interdisciplinary areas.

著者

安村 禎明 武市 雅司 新田 克己

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.4, pp.212-220, 2003 (Released:2003-05-20)

参考文献数

14

被引用文献数

3 8 10

---

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

梶村 俊介 馬場 雪乃 梶野 洸 鹿島 久嗣

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.2, pp.K-F79_1-9, 2016-03-01 (Released:2016-02-18)

参考文献数

20

---

Crowdsourcing allows human intelligence tasks to be outsourced to a large number of unspecified people at low costs. However, because of the uneven ability and diligence of crowd workers, the quality of their work is also uneven and sometimes quite low. Therefore, quality control is one of the central issues in crowdsourcing research. In this paper, we address a quality control problem of enumeration tasks, in which workers are asked to enumerate as many answers satisfying certain conditions as possible. As examples of enumeration tasks, we consider text collection tasks in addition to POI collection tasks. Since workers neither necessarily provide correct answers nor provide exactly the same answers even if the answers indicate the same object because of orthographic or numerical variations, we propose a two-stage quality control method consisting of an answer clustering stage and a reliability estimation stage. The answer clustering stage with a new constrained exemplar clustering method groups answers indicating the same object into a cluster and requires a representative answer from each cluster, and then the reliability estimation stage with a modified HITS estimates the reliabilities of representative answers and removes unreliable ones. Implemented with a new constrained exemplar clustering and a modified HITS algorithm, the effectiveness of our method is demonstrated as compared to baseline methods on several real crowdsourcing datasets of POI collection tasks and text collection tasks.

著者

土坂 恭斗 尾関 基行 岡 夏樹

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.1, pp.213-218, 2014

---

Pokémon is one of the most famous video games, which has more than 3.4 million players around the world. The interesting part of this game is to guess invisible information and the character of the opponent. However, existing Non Player Character (NPC) of this game is not a good alternative opponent to a human player because the NPC does not have variety of characteristics. In this paper, we propose a novel method to represent reflection - impulsivity characteristics of NPC by differences of the first stage prior distribution in Bayesian estimation used for decision-making of the NPC. In the experiment, we ask human players to take on three types of the proposed NPC and to answer the impression of those NPCs. As the result, the players feel different impressions from the three types of NPCs although they cannot identify the three types of the character (reflection - intermediate - impulsivity).

著者

佐々木 一磨 北岡 伸也 小田桐 優理

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.5, pp.B-MB2_1-8, 2023-09-01 (Released:2023-09-01)

参考文献数

35

---

Pose generation plays an essential role in computer graphics, such as game character design, and 3D modeling. Rather than inverse Kinematics solvers using deterministic heuristic methods suffering from poor diversity, sample-based methods promise to generate a wider variety of poses satisfying the given constraints. In order to obtain generative models from sample data, Generative Adversarial Networks (GANs) are widely used in many problems including pose generation. However, GANs are known to be suffering from mode collapse which causes the generation of specific patterns. Therefore, we propose a novel generative model for pose generation using Implicit Maximum Likelihood Estimation (IMLE), which is a training method for avoiding mode collapse by adaptive sampling of the input-output pairs. The proposed model accepts not only the latent variable, but also the condition of the pose such as a position of the kinematic model’s joint. We trained the proposed model by the IMLE’s optimization method using the dataset consisting of the pair of the pose condition and the corresponding joint angles. In the experiment of a simulated 3-DoF arm simulation, the proposed model successfully avoided mode collapse, thus better diversity rather than the GAN variants while satisfying the given conditional input. Furthermore, we report that the proposed model performs lower prediction error and higher variance than the GAN variants through the experiments on 30-DoF human pose using CMU Mocap Dataset.

著者

船越 孝太郎

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.37, no.6, pp.C-M11_1-18, 2022-11-01 (Released:2022-11-01)

参考文献数

69

---

This paper presents Non-Axiomatic Term Logic (NATL) as a theoretical computational framework of humanlike symbolic reasoning in artificial intelligence. NATL unites a discrete syntactic system inspired from Aristotle’s term logic and a continuous semantic system based on the modern idea of distributed representations, or embeddings. This paper positions the proposed approach in the phylogeny and the literature of logic, and explains the framework. As it is yet no more than a theory and it requires much further elaboration to implement it, no quantitative evaluation is presented. Instead, qualitative analyses of arguments using NATL, some applications to possible cognitive science/robotics-related research, and remaining issues towards a machinery implementation are discussed.

著者

岩永 二郎 西村 直樹 鮏川 矩義 高野 祐一

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.37, no.3, pp.D-L74_1-11, 2022-05-01 (Released:2022-05-01)

参考文献数

23

---

Many mothers have considerable anxiety about pregnancy, childbirth, and childcare. For such mothers, searching for information on the Internet is an effective means of dissolving their anxieties. We consider the problem of estimating, for each search word, a distribution of search dates with respect to children’s birth dates. Most of the empirical distributions have unimodal or bimodal shapes, and some of them are asymmetric about extremal points and rise or fall sharply. We propose nonparametric estimation methods based on mathematical optimization models for such probability distributions. Our unimodal and bimodal optimization models automatically estimate the optimal extremal points and can be extended to multimodal distributions. These models are formulated as mixed-integer convex quadratic optimization problems, which can be solved exactly using optimization software. Experimental results using real-world and synthetic datasets demonstrate that our methods are effective by comparison to conventional moving average and kernel estimation methods.

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

---

<p>"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.</p><p>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.</p><p>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.</p><p>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.</p>

著者

﨑下 雅仁 小川 ちひろ 土屋 賢治 岩渕 俊樹 岸本 泰士郎 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.3, pp.B-J45_1-11, 2020-05-01 (Released:2020-05-01)

参考文献数

28

---

In recent years, population with autism spectrum disorder (ASD) are growing explosively, and diagnosis of ASD is difficult due to difference of interviewers and environments, etc. We show relations between utterance features and ASD severity scores, which were manually given by a clinical psychologist. These scores are of the Autism Diagnostic Observation Schedule (ADOS), which is one of the standard metrics for symptom evaluation for subjects who are suspected as ASD. We built our original corpus where we transcribed voice records of our ADOS evaluation experiment movies. Our corpus is the world largest as speech/dialog of ASD subjects, and there has been no such ADOS corpus available in Japanese language as far as we know. We investigated relationships between ADOS scores (severity) and utterance features we defined. Our system automatically estimated their scores using support vector regression (SVR). Our average estimation errors were around error rates that human ADOS experts are required not to exceed. Because our detailed analysis for each part of the ADOS test (“puzzle toy assembly + story telling” part and the “depiction of a picture” part) shows different error rates, effectiveness of our features would depend on the contents of the records. By comparing an ADOS score prediction result of adults and adults with that of children, we showed common features of ADOS scores between children and adults. Our entire results suggest a new automatic way to assist humans’ diagnosis, which could help supporting language rehabilitation for patients with ASD in future.

著者

松尾 豊 石塚 満

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.17, no.3, pp.217-223, 2002 (Released:2002-04-04)

参考文献数

24

被引用文献数

6 18

---

We present a new keyword extraction algorithm that applies to a single document without using a large corpus. Frequent terms are extracted first, then a set of co-occurrence between each term and the frequent terms, i.e., occurrences in the same sentences, is generated. The distribution of co-occurrence shows the importance of a term in the document as follows. If the probability distribution of co-occurrence between term a and the frequent terms is biased to a particular subset of the frequent terms, then term a is likely to be a keyword. The degree of the biases of the distribution is measured by χ²-measure. We show our algorithm performs well for indexing technical papers.

著者

村井 源 徃住 彰文

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.6, pp.473-481, 2006 (Released:2006-08-23)

参考文献数

20

被引用文献数

5

---

This paper introduces a method of representing in a network the thoughts of individual authors of dogmatic texts numerically and objectively by means of co-citation analysis and a method of distinguishing between the thoughts of various authors by clustering and analysis of clustered elements, generated by the clustering process. Using these methods, this paper creates and analyzes the co-citation networks for five authoritative Christian theologians through history (Augustine, Thomas Aquinas, Jean Calvin, Karl Barth, John Paul II). These analyses were able to extract the core element of Christian thought (Jn 1:14, Ph 2:6, Ph 2:7, Ph 2:8, Ga 4:4), as well as distinctions between the individual theologians in terms of their sect (Catholic or Protestant) and era (thinking about the importance of God's creation and the necessity of spreading the Gospel). By supplementing conventional literary methods in areas such as philosophy and theology, with these numerical and objective methods, it should be possible to compare the characteristics of various doctrines. The ability to numerically and objectively represent the characteristics of various thoughts opens up the possibilities of utilizing new information technology, such as web ontology and the Artificial Intelligence, in order to process information about ideological thoughts in the future.

著者

松原 正樹 諏訪 正樹 斎藤 博昭

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.27, no.5, pp.281-295, 2012 (Released:2012-09-26)

参考文献数

50

被引用文献数

2

---

This paper describes an interactive learning-aid system for analytical comprehension of music by highlighting orchestral score in colors, and classifies and evaluates the learning process on the system. An orchestral music is composed to integrate many instrumental parts, and musicians have to be proficient in reading the score analytically in order to understand its multifaceted structure. However, many people often face difficulty in comprehending its musical structure: Some intermediate performers can read and perform their own part, but cannot understand the role of each part in the assembled whole. In order to solve this problem, our conventional paper proposes an interactive supportive system called ScoreIlluminator that enables musicians (and non-musicians) to easily represent how he or she recognizes an orchestral music, e.g. the differentiation of melody parts from the others, and the similarity across instrumental parts. ScoreIlluminator clusters the parts from an orchestral score according to their roles in the whole, and displays the clusters on the score by assigning a color to each cluster. The users can manipulate the clustering parameters with the user interface of the system. The system employs two major design concepts. One is ``colored notation'' and the other is ``directability''. The ``colored notation'' visualizes the roles and the relations between parts, which are estimated by the system. The estimation is based on the similarity metric of four musical features: rhythmic activity, sonic richness, melodic activity and consonance activity. Using these metrics, clustering phase is conducted using an unsupervised learning algorithm (k-means algorithm). Our system provides the ``directability'' with an interactive interface in which subjects can freely manipulate parameter settings and see the change in score-highliting in real-time. In this process, users learn the role of parts and the relationship between parts and explore multifaceted interpretations of the music. To verify the effectiveness of the system, we conducted a user-experience experiment with four intermediate musicians. The musicians showed various kinds of progress in interpreting the score. With the episodes from the experiment, we discuss how the system encouraged subject's analytic skill in orchestral-score reading and music listening.

著者

西銘 大喜 遠藤 聡志 當間 愛晃 山田 孝治 赤嶺 有平

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.32, no.5, pp.F-H34_1-8, 2017-09-01 (Released:2017-09-01)

参考文献数

20

被引用文献数

6

---

Facial expressions play an important role in communication as much as words. In facial expression recognition by human, it is difficult to uniquely judge, because facial expression has the sway of recognition by individual difference and subjective recognition. Therefore, it is difficult to evaluate the reliability of the result from recognition accuracy alone, and the analysis for explaining the result and feature learned by Convolutional Neural Networks (CNN) will be considered important. In this study, we carried out the facial expression recognition from facial expression images using CNN. In addition, we analysed CNN for understanding learned features and prediction results. Emotions we focused on are “happiness”, “sadness”, “surprise”, “anger”, “disgust”, “fear” and “neutral”. As a result, using 32286 facial expression images, have obtained an emotion recognition score of about 57%; for two emotions (Happiness, Surprise) the recognition score exceeded 70%, but Anger and Fear was less than 50%. In the analysis of CNN, we focused on the learning process, input and intermediate layer. Analysis of the learning progress confirmed that increased data can be recognised in the following order “happiness”, “surprise”, “neutral”, “anger”, “disgust”, “sadness” and “fear”. From the analysis result of the input and intermediate layer, we confirmed that the feature of the eyes and mouth strongly influence the facial expression recognition, and intermediate layer neurons had active patterns corresponding to facial expressions, and also these activate patterns do not respond to partial features of facial expressions. From these results, we concluded that CNN has learned the partial features of eyes and mouth from input, and recognise the facial expression using hidden layer units having the area corresponding to each facial expression.

著者

伊藤 詩乃 田中 佑岳 狩野 芳伸 榊原 康文

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-G_1-9, 2016-11-01 (Released:2016-11-22)

参考文献数

22

---

In recent years, the digitization of medical and health data including clinical data, health diagnostic data, medication log data have been made rapidly. One potential application using electronic medical and health information is to develop a system to make a medical diagnosis according to the contents recorded in the electronic medical data and the appropriate patient information. The task of understanding the condition of the patient and making precisely the diagnosis is hard to be automated and requires the high degree of expertise. Toward a final goal to construct a medical diagnostic support system, as its pilot study, we attempt to build a question-answering program that automatically answers the medical licensing examination. The national medical licensing examination is the form of multiple-choice test and contains a wide variety of problems. There is a type of problems to answer the appropriate disease name among multiple choices given the patient information and test results as a problem statement. We aimed to develop the program to answer this type of questions. By the development of such question-answering program that automatically answers the medical licensing examination, we revealed the fundamental issues and essential difficulties in the information processing of the medical data, and finally constructed the foundation for conducting disease diagnosis support with patient information. In this paper, we developed a question-answering program and actually performed the answering for some problems in 107th and 108th out of national medical licensing examination. We carefully examined and analyzed the results and problems that could be answered correctly and problems that were given incorrect answers, and proposed the improvements to build a more accurate program.

著者

髙橋 寛治 竹野 峻輔 山本 和英

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.D-H33_1-4, 2017-09-01 (Released:2017-09-01)

参考文献数

7

被引用文献数

1

---

This paper presents a novel metric for evaluating stability of machine translation system. A stable system indicates that it keeps almost the same outputs given the inputs with slight changes. In this paper, we propose a stability metric by exploiting TER metric for evaluating the differences between the two texts. We have built an evaluation data set, and demonstrate that a neural-based method is unstable rather than a statistical-based method, while the former outperforms the latter.