著者
Nurul Lubis Sakriani Sakti Koichiro Yoshino 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.33, no.1, pp.DSH-D_1-10, 2018-01-01 (Released:2018-01-31)
参考文献数
29
被引用文献数
2

To completely mimic the naturalness of human interaction in Human-Computer Interaction (HCI), emotion is an essential aspect that should not be overlooked. Emotion allows for a rich and meaningful human interaction. In communicating, not only we express our emotional state, but we are also affected by our conversational counterpart. However, existing works have largely focused only on occurrences of emotion through recognition and simulation. The relationship between an utterance of a speaker and the resulting emotional response that it triggers is not yet closely examined. Observation and incorporation of the underlying process that causes change of emotion can provide useful information for dialogue systems in making a more emotionally intelligent decision, such as being able to take proper action with regard to user’s emotion, and to be aware of the emotional implication of their response. To bridge this gap, in this paper, we tackle three main tasks: 1) recognition of emotional states, 2) analysis of social-affective events in spontaneous conversational data, to capture the relationship between actions taken in discourse and the emotional response that follows, and 3) prediction of emotional triggers and responses in a conversational context. The proposed study differs from existing works in that it focuses on the change of emotion (emotional response) and its cause (emotional triggers) on top of the occurrence of emotion itself. The analysis and experimental results are reported in detail in this paper, showing promising initial results for future works and development.
著者
Ryo Fukuda Katsuhito Sudoh Satoshi Nakamura
出版者
The Association for Natural Language Processing
雑誌
自然言語処理 (ISSN:13407619)
巻号頁・発行日
vol.29, no.2, pp.344-366, 2022 (Released:2022-06-15)
参考文献数
42

Recent studies consider knowledge distillation as a promising method for speech translation (ST) using end-to-end models. However, its usefulness in cascade ST with automatic speech recognition (ASR) and machine translation (MT) models has not yet been clarified. An ASR output typically contains speech recognition errors. An MT model trained only on human transcripts performs poorly on error-containing ASR results. Thus, it should be trained considering the presence of ASR errors during inference. In this paper, we propose using knowledge distillation for training of the MT model for cascade ST to achieve robustness against ASR errors. We distilled knowledge from a teacher model based on human transcripts to a student model based on erroneous transcriptions. Our experimental results showed that the proposed method improves the translation performance on erroneous transcriptions. Further investigation by combining knowledge distillation and fine-tuning consistently improved the performance on two different datasets: MuST-C English--Italian and Fisher Spanish--English.
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
Hiroaki Tanaka Yu Suzuki Shotaro Yamasaki Koichiro Yoshino Ko Kato Satoshi Nakamura
出版者
Information Processing Society of Japan
雑誌
IPSJ Transactions on Bioinformatics (ISSN:18826679)
巻号頁・発行日
vol.11, pp.14-23, 2018 (Released:2018-07-05)
参考文献数
43

Protein production in plants is a hot topic because there are many benefits relative to bacteria, yeasts, and animals, but the amount of protein expression in plants is less. It is argued that editing 5'UTRs increases the amount of translated proteins. However, obtaining such 5'UTRs is difficult due to the cost, time and effort required in experiments. To solve this, we predict the amount of translated proteins by machine learning. In this paper, we propose a method, named “R-STEINER, ” that generates 5'UTRs that increase the amount of proteins of a given gene. The proposed process involves building a model for predicting the amount of translated proteins, generating 5'UTRs, selecting them and increasing the proteins according to the model. This method enables us to obtain 5'UTRs that increase the amount of translated proteins without real synthesis experiments, resulting in reduced cost, time and effort. In our study, we built a prediction model for Oryza sativa and synthesized the 5'UTRs generated by R-STEINER. We confirmed that the model can predict the amount of translated proteins with a correlation coefficient of 0.89.
著者
Kosuke Takahashi Katsuhito Sudoh Satoshi Nakamura
出版者
The Association for Natural Language Processing
雑誌
自然言語処理 (ISSN:13407619)
巻号頁・発行日
vol.29, no.1, pp.3-22, 2022 (Released:2022-03-15)
参考文献数
23
被引用文献数
1

As the performance of machine translation has improved, the need for a human-like automatic evaluation metric has been increasing. The use of multiple reference translations against a system translation (a hypothesis) has been adopted as a strategy to improve the performance of such evaluation metrics. However, preparing multiple references is highly expensive and impractical. In this study, we propose an automatic evaluation method for machine translation that uses source sentences as additional pseudo-references. The proposed method evaluates a translation hypothesis via regression to assign a real-valued score. The model takes the paired source, reference, and hypothesis sentences together as input. A pre-trained large-scale cross-lingual language model encodes the input to sentence vectors, with which the model predicts a human evaluation score. The results of experiments show that our proposed method exhibited stably higher correlation with human judgements than baseline methods that solely depend on hypothesis and reference sentences, especially when the hypotheses were very high- or low-quality translations.
著者
Seiya Kawano Koichiro Yoshino 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.36, no.4, pp.E-KC9_1-14, 2021-07-01 (Released:2021-07-01)
参考文献数
48

Building a controllable neural conversation model (NCM) is an important task. In this paper, we focus on controlling the responses of NCMs using dialogue act labels of responses as conditions. We introduce a reinforcement learning framework involving adversarial learning for conditional response generation. Our proposed method has a new label-aware objective that encourages the generation of discriminative responses by the given dialogue act label while maintaining the naturalness of the generated responses. We compared the proposed method with conventional methods that generate conditional responses. The experimental results showed that our proposed method has higher controllability conditioned by the dialogue acts even though it has higher or comparable naturalness to the conventional models.
著者
Chushi Kuroiwa Phengta Vongphrachanh Phoxay Xayyavong Kongmany Southalack Masahiro Hashizume Satoshi Nakamura
出版者
日本疫学会
雑誌
Journal of Epidemiology (ISSN:09175040)
巻号頁・発行日
vol.11, no.6, pp.255-262, 2001 (Released:2007-11-30)
参考文献数
22
被引用文献数
5 5

Following the Pan American Health Organization (PAHO) recommendation on measles elimination, the Western Pacific Region of WHO (WPR) is emphasizing accelerated measles control programme especially since the achievement of polio eradication in WPR in 2000. This includes upgraded surveillance and mass measles vaccination campaign for children aged 9 months to 4 years. However, there are limited scientific evidences supporting the feasibility of this programme in Laos. To examine measles elimination feasibility in the country, we conducted measles outbreak investigation using immunoglobulin M (IgM). From March 1999 to March 2000, we conducted 7 outbreak investigations. At the outbreak sites, we examined clinical manifestations of cases and collected individual data. About five blood samples were drawn from each outbreak, and lgM antibodies to measles were tested. Of 7 investigated outbreaks, 5 were confirmed as measles, one was chickenpox, and one occurred in the inaccessible area due to flooding. In a village of high land Lao, blood drawn was refused. Of 185 cases, 64 (34.6%) cases were immunized, and 110 (59.5%) were unimunized. The estimated vaccine efficacy is 67.9%. The number of measles cases among school-aged children was 74 (40.0%), which represented 2.5% of the total population in investigated villages. Our findings showed various difficulties of the surveillance and the limited outcomes of mass measles vaccination campaign under the accelerated measles control programme by WPR. Efforts to improve cold chain as well as increasing routine immunization coverage must be the priority of measles control. J Epidemiol, 2001 ; 11 : 255-262
著者
Masafumi Takafuji Masaki Ishida Satoshi Nakamura Kei Nakata Haruno Ito Takanori Kokawa Kensuke Domae Suguru Araki Shiro Nakamori Junko Ishiura Kaoru Dohi Hajime Sakuma
出版者
Japanese Society for Magnetic Resonance in Medicine
雑誌
Magnetic Resonance in Medical Sciences (ISSN:13473182)
巻号頁・発行日
pp.mp.2023-0018, (Released:2023-09-28)
参考文献数
37

Purpose: The purposes of this study were to compare global coronary flow reserve (CFR) between patients with idiopathic dilated cardiomyopathy (DCM) and risk-matched controls using cardiac MRI (CMR), and to evaluate the relationship between global CFR and CMR left ventricular (LV) parameters.Methods: Twenty-six patients with DCM and 26 risk-matched controls who underwent comprehensive CMR examination, including stress-rest coronary sinus flow measurement by phase contrast (PC) cine CMR were retrospectively studied. LV peak global longitudinal, radial, and circumferential strains (GLS, GRS, and GCS) were determined by feature tracking.Results: Patients with DCM had significantly lower global CFR compared with the risk-matched controls (2.87 ± 0.86 vs. 4.03 ± 1.47, P = 0.001). Among the parameters, univariate linear regression analyses revealed significant correlation of global CFR with LV end-diastolic volume index (r = –0.396, P = 0.045), LV mass index (r = –0.461, P = 0.018), GLS (r = –0.558, P = 0.003), and GRS (r = 0.392, P = 0.047). Multiple linear regression analysis revealed GLS as the only independent predictor of global CFR (standardized β = –0.558, P = 0.003).Conclusion: Global CFR was significantly impaired in patients with idiopathic DCM and independently associated with LV GLS, suggesting that microvascular dysfunction may contribute to deterioration of LV function in patients with idiopathic DCM.
著者
Yui Oka Katsuhito Sudoh Satoshi Nakamura
出版者
The Association for Natural Language Processing
雑誌
自然言語処理 (ISSN:13407619)
巻号頁・発行日
vol.28, no.3, pp.778-801, 2021 (Released:2021-09-15)
参考文献数
25

Neural machine translation often suffers from an under-translation problem owing to its limited modeling of the output sequence lengths. In this study, we propose a novel approach to training a Transformer model using length constraints based on length-aware positional encoding (PE). Because length constraints with exact target sentence lengths degrade the translation performance, we add a random perturbation with a uniform distribution within a certain range to the length constraints in the PE during the training. In the inference step, we predicted the output lengths from the input sequences using a length prediction model based on a large-scale pre-trained language model. In Japanese-to-English and English-to-Japanese translation, experimental results show that the proposed perturbation injection improves the robustness of the length prediction errors, particularly within a certain range.
著者
Yoshiki MAKI Yuji SHIRATORI Kenta SATO Satoshi NAKAMURA
出版者
Japan Society of Kansei Engineering
雑誌
International Symposium on Affective Science and Engineering (ISSN:24335428)
巻号頁・発行日
pp.1-6, 2018 (Released:2018-11-01)
参考文献数
8
被引用文献数
1

Previous studies suggested that spoilers might increase the enjoyment of novels. However, the problem of spoilers has not been sufficiently clarified. The objective of our work is to clarify the effect of comic spoilers and to apply clarified knowledge for applications. In our past work, we constructed a spoiler dataset and investigated the spoilers’ effect by changing the spoiler timing for readers. However, in the past work, we could not clarify the characteristics of spoilers. In this work, we clarified that spoilers reduced the interest in continuing reading the comics and analyzed the characteristics of spoilers by using the dataset. Then, we considered how to construct a comic spoiler dataset and investigated how to determine the spoiling pages automatically using image processing, and character detection and so on.
著者
Ikuo KESHI Yu SUZUKI Koichiro YOSHINO Satoshi NAKAMURA
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE Transactions on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E101.D, no.4, pp.1066-1078, 2018-04-01 (Released:2018-04-01)
参考文献数
24
被引用文献数
1

The problem with distributed representations generated by neural networks is that the meaning of the features is difficult to understand. We propose a new method that gives a specific meaning to each node of a hidden layer by introducing a manually created word semantic vector dictionary into the initial weights and by using paragraph vector models. We conducted experiments to test the hypotheses using a single domain benchmark for Japanese Twitter sentiment analysis and then evaluated the expandability of the method using a diverse and large-scale benchmark. Moreover, we tested the domain-independence of the method using a Wikipedia corpus. Our experimental results demonstrated that the learned vector is better than the performance of the existing paragraph vector in the evaluation of the Twitter sentiment analysis task using the single domain benchmark. Also, we determined the readability of document embeddings, which means distributed representations of documents, in a user test. The definition of readability in this paper is that people can understand the meaning of large weighted features of distributed representations. A total of 52.4% of the top five weighted hidden nodes were related to tweets where one of the paragraph vector models learned the document embeddings. For the expandability evaluation of the method, we improved the dictionary based on the results of the hypothesis test and examined the relationship of the readability of learned word vectors and the task accuracy of Twitter sentiment analysis using the diverse and large-scale benchmark. We also conducted a word similarity task using the Wikipedia corpus to test the domain-independence of the method. We found the expandability results of the method are better than or comparable to the performance of the paragraph vector. Also, the objective and subjective evaluation support each hidden node maintaining a specific meaning. Thus, the proposed method succeeded in improving readability.
著者
Toru WATANABE Takayuki MIURA Tsukasa SASAKI Satoshi NAKAMURA Tatsuo OMURA
出版者
Japan Society of Civil Engineers
雑誌
ENVIRONMENTAL ENGINEERING RESEARCH (ISSN:13415115)
巻号頁・発行日
vol.43, pp.245-254, 2006-11-17 (Released:2011-06-27)
参考文献数
12
被引用文献数
1

メコン流域の一部の地域では, 安全な水供給を目的として, 先進国と同様に浄水場と管路網からなる広 域水道と, 集落単位で地下水をくみ上げて配水する簡易な水道 (集落水道) がそれぞれ整備されている。これらの水供給システムによる感染リスク低減効果を明らかにするために, 2つのケーススタディを実施した。タイにおけるケーススタディでは, 広域水道と集落水道の整備地域で, 飲用水起因の感染症のリスクを比較した。その結果, 塩素消毒後の安全な水が供給される広域水道整備地域のリスクは, 集落水道整備地域の約1/8であった。カンボジアにおけるケーススタディでは, 集落水道整備地域と水道未整備地域のリスクを比較し, 集落水道整備地域の方が1/5程度にリスクが低下する結果を得た。
著者
Shigeki MATSUDA Teruaki HAYASHI Yutaka ASHIKARI Yoshinori SHIGA Hidenori KASHIOKA Keiji YASUDA Hideo OKUMA Masao UCHIYAMA Eiichiro SUMITA Hisashi KAWAI Satoshi NAKAMURA
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E100-D, no.4, pp.621-632, 2017-04-01

This study introduces large-scale field experiments of VoiceTra, which is the world's first speech-to-speech multilingual translation application for smart phones. In the study, approximately 10 million input utterances were collected since the experiments commenced. The usage of collected data was analyzed and discussed. The study has several important contributions. First, it explains system configuration, communication protocol between clients and servers, and details of multilingual automatic speech recognition, multilingual machine translation, and multilingual speech synthesis subsystems. Second, it demonstrates the effects of mid-term system updates using collected data to improve an acoustic model, a language model, and a dictionary. Third, it analyzes system usage.