Li Jiyi(Faculty of Information Science and Technology　Computer Science and Information Technology　Knowledge Software Science)

User-experience oriented POI recommendation with pseudo rating
Kun Yi; Ryu Yamagishi; Jiyi Li; Taishan Li; Zhengyang Bai; Qiang Ma
Multimedia Tools and Applications, Springer Science and Business Media LLC, 28 Jun. 2024
Scientific journal

Voices of the Himalayas: Benchmarking Speech Recognition Systems for the Tibetan Language
Sheng Li; Jiyi Li; Chenhui Chu
International Journal of Asian Language Processing, World Scientific Pub Co Pte Ltd, 31 May 2024
Scientific journal

Phantom in the opera: adversarial music attack for robot dialogue system
Sheng Li; Jiyi Li; Yang Cao
Frontiers in Computer Science, 6, Frontiers Media SA, 15 Feb. 2024
Scientific journal, This study explores the vulnerability of robot dialogue systems' automatic speech recognition (ASR) module to adversarial music attacks. Specifically, we explore music as a natural camouflage for such attacks. We propose a novel method to hide ghost speech commands in a music clip by slightly perturbing its raw waveform. We apply our attack on an industry-popular ASR model, namely the time-delay neural network (TDNN), widely used for speech and speaker recognition. Our experiment demonstrates that adversarial music crafted by our attack can easily mislead industry-level TDNN models into picking up ghost commands with high success rates. However, it sounds no different from the original music to the human ear. This reveals a serious threat by adversarial music to robot dialogue systems, calling for effective defenses against such stealthy attacks.

AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses.
Xiaotian Lu; Jiyi Li; Koh Takeuchi 0001; Hisashi Kashima
Findings of the Association for Computational Linguistics: EMNLP 2024, 1847, 1856, Association for Computational Linguistics, 2024
International conference proceedings

AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses.
Xiaotian Lu; Jiyi Li; Koh Takeuchi 0001; Hisashi Kashima
CoRR, abs/2410.01246, 2024
Scientific journal

A Generalized Model for Multidimensional Intransitivity.
Jiuding Duan; Jiyi Li; Yukino Baba; Hisashi Kashima
CoRR, abs/2409.19325, 2024
Scientific journal

Evaluating Saliency Explanations in NLP by Crowdsourcing.
Xiaotian Lu; Jiyi Li; Zhen Wan; Xiaofeng Lin 0001; Koh Takeuchi 0001; Hisashi Kashima
CoRR, abs/2405.10767, 2024
Scientific journal

Evaluating Saliency Explanations in NLP by Crowdsourcing.
Xiaotian Lu; Jiyi Li; Zhen Wan; Xiaofeng Lin 0001; Koh Takeuchi 0001; Hisashi Kashima
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation(LREC/COLING), 6431, 6443, ELRA and ICCL, 2024
International conference proceedings

FedCPC: An Effective Federated Contrastive Learning Method for Privacy Preserving Early-Stage Alzheimers Speech Detection
Wenqing Wei; Zhengdong Yang; Yuan Gao; Jiyi Li; Chenhui Chu; Shogo Okada; Sheng Li
2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), IEEE, 16 Dec. 2023
International conference proceedings

Reprogramming Self-supervised Learning-based Speech Representations for Speaker Anonymization
Xiaojiao Chen; Sheng Li; Jiyi Li; Hao Huang; Yang Cao; Liang He
ACM Multimedia Asia 2023, ACM, 06 Dec. 2023
International conference proceedings

GhostVec: A New Threat to Speaker Privacy of End-to-End Speech Recognition System
Xiaojiao Chen; Sheng Li; Jiyi Li; Yang Cao; Hao Huang; Liang He
ACM Multimedia Asia 2023, ACM, 06 Dec. 2023
International conference proceedings

Correction while Recognition: Combining Pretrained Language Model for Taiwan-Accented Speech Recognition
Sheng Li; Jiyi Li
Artificial Neural Networks and Machine Learning – ICANN 2023, 389, 400, Springer Nature Switzerland, 22 Sep. 2023
In book

An End-to-End Chinese and Japanese Bilingual Speech Recognition Systems with Shared Character Decomposition
Sheng Li; Jiyi Li; Qianying Liu; Zhuo Gong
Communications in Computer and Information Science, 493, 503, Springer Nature Singapore, 14 Apr. 2023, [Peer-reviewed]
English, In book

Multiview Representation Learning from Crowdsourced Triplet Comparisons.
Xiaotian Lu; Jiyi Li; Koh Takeuchi 0001; Hisashi Kashima
Proceedings of the ACM Web Conference 2023(WWW), 3827, 3836, ACM, 2023
International conference proceedings

CC-Glasses: Color Communication Support for People with Color Vision Deficiency Using Augmented Reality and Deep Learning.
Zhenyang Zhu; Jiyi Li; Ying Tang 0003; Kentaro Go; Masahiro Toyoura; Kenji Kashiwagi; Issei Fujishiro; Xiaoyang Mao
Proceedings of the Augmented Humans International Conference 2023(AHs), 190, 199, ACM, 2023
International conference proceedings

Augmented Adversarial Self-Supervised Learning for Early-Stage Alzheimer's Speech Detection
Longfei Yang; Wenqing Wei; Sheng Li; Jiyi Li; Takahiro Shinozaki
in Proc. INTERSPEECH, Sep. 2022, [Peer-reviewed]
English, International conference proceedings

Multi-Domain Dialogue State Tracking with Top-K Slot Self Attention.
Longfei Yang; Jiyi Li; Sheng Li 0010; Takahiro Shinozaki
Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue(SIGDIAL), 231, 236, Association for Computational Linguistics, 2022
International conference proceedings

Improving Pairwise Rank Aggregation via Querying for Rank Difference.
Guoxi Zhang; Jiyi Li; Hisashi Kashima
9th IEEE International Conference on Data Science and Advanced Analytics(DSAA), 1, 9, IEEE, 2022
International conference proceedings

A Multi-task based Bilateral-Branch Network for Imbalanced Citation Intent Classification
Tianxiang Hu; Jiyi Li; Fumiyo Fukumoto; Renjie Zhou
Proceedings of the 2022 international conference on ubiquitous information management and communication (IMCOM 2022), 1, 8, Jan. 2022, [Peer-reviewed]
English, International conference proceedings

Label Aggregation for Crowdsourced Triplet Similarity Comparisons
Jiyi Li; Lucas Ryo Endo; Hisashi Kashima
Proceedings of the 28th International Conference on Neural Information Processing (ICONIP 2021), 176, 185, Dec. 2021, [Peer-reviewed]
English, International conference proceedings

Neural Local and Global Contexts Learning for Word Sense Disambiguation
Fumiyo Fukumoto; Taishin Mishima; Jiyi Li; Yoshimi Suzuki
Proceedings of the 28th International Conference on Neural Information Processing (ICONIP 2021), 537, 549, Dec. 2021, [Peer-reviewed]
English, International conference proceedings

Paraphrase Identification with Neural Elaboration Relation Learning
Sheng Xu; Fumiyo Fukumoto; Jiyi Li; Yoshimi Suzuki
Proceedings of the 28th International Conference on Neural Information Processing (ICONIP 2021), 562, 573, Dec. 2021, [Peer-reviewed]
English, International conference proceedings

Abstract, Rationale, Stance: A Joint Model for Scientific Claim Verification
Zhiwei Zhang; Jiyi Li; Fumiyo Fukumoto; Yanming Ye
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021), 3580, 3586, Nov. 2021, [Peer-reviewed]
English, International conference proceedings

Happy Text Entering: Promoting Subjective Well-being using an Input Method for Presenting Positive Words and Phrases
Kentaro Go; Yuki Moriya; Yuichiro Kinoshita; Jiyi Li; Fumiyo Fukumoto
Proceedings of the 33rd Australian Conference on Human-Computer Interaction (OzCHI 2021) Late-Breaking Works, ACM, Nov. 2021, [Peer-reviewed]
English, International conference proceedings

Learning from Multiple Annotators by Incorporating Instance Features
Jingzheng Li; Hailong Sun; Jiyi Li; Zhijun Chen; Renshuai Tao; Yufei Ge
IJCAI 2021 Workshop on Weakly Supervised Representation Learning (IJCAI 2021 WSRL Workshop 2021), Aug. 2021, [Peer-reviewed]
English, Symposium

Multi-task Neural Shared Structure Search: A Study based on Text Mining
Jiyi Li; Fumiyo Fukumoto
Proceeding of the 26th International Conference on Database Systems for Advanced Applications (DASFAA 2021), 202, 218, Apr. 2021, [Peer-reviewed]
English, International conference proceedings

A Neural Local Coherence Analysis Model for Clarity Text Scoring
Panitan Muangkammuen; Sheng Xu; Fumiyo Fukumoto; Kanda Runapongsa Saikaew; Jiyi Li
The 28th International Conference on Computational Linguistics (COLING 2020), Dec. 2020, [Peer-reviewed]
English, International conference proceedings

HSCNN: A Hybrid-Siamese Convolutional Neural Network for Extremely Imbalanced Multi-label Text Classification
Wenshuo Yang; Jiyi Li; Fumiyo Fukumoto; Yanming Ye
the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), 6716, 6722, Nov. 2020, [Peer-reviewed]
English, International conference proceedings

Multi-task Peer-Review Score Prediction
Jiyi Li; Ayaka Sato; Kazuya Shimura; Fumiyo Fukumoto
The First Workshop on Scholarly Document Processing (SDP 2020, conjunction with EMNLP2020), 121, 126, Nov. 2020, [Peer-reviewed]
English, International conference proceedings

AffectI: A Game for Diverse, Reliable, and Efficient Affective Image Annotation
Xingkun Zuo; Jiyi Li; Qili Zhou; Jianjun Li; Xiaoyang Mao
the 28th ACM International Conference on Multimedia (MM 2020), 529, 537, Oct. 2020, [Peer-reviewed]
English, International conference proceedings

CrowDEA: Multi-view Idea Prioritization with Crowds
Yukino Baba; Jiyi Li; Hisashi Kashima
the eighth AAAI Conference on Human Computation and Crowdsourcing (HCOMP 2020), 8, 1, 23, 32, Oct. 2020, [Peer-reviewed]
English, International conference proceedings

Crowdsourced Text Sequence Aggregation based on Hybrid Reliability and Representation
Jiyi Li
the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2020), 1761, 1764, Jul. 2020, [Peer-reviewed]
English, International conference proceedings

Performance as a Constraint: An Improved Wisdom of Crowds Using Performance Regularization
Jiyi Li; Yasushi Kawase; Yukino Baba; Hisashi Kashima
the 29th International Joint Conference on Artificial Intelligence (IJCAI 2020), 1534, 1541, Jul. 2020, [Peer-reviewed]
English, International conference proceedings

DeepMet: A Reading Comprehension Paradigm for Token-level Metaphor Detection
Chuandong Su; Fumiyo Fukumoto; Xiaoxi Huang; Jiyi Li; Rongbo Wang; Zhiqun Che
The Second Workshop on Figurative Language Processing (FigLang 2020, conjunction with ACL 2020), 30, 39, Jul. 2020, [Peer-reviewed]
English, International conference proceedings

English and Chinese Neural Metonymy Recognition Based on Semantic Priority Interruption Theory
Chuandong Su; Xiaoxi Huang; Fumiyo Fukumoto; Jiyi Li; Rongbo Wang; Zhiqun Chen
IEEE Access, 30060, 30068, 2020, [Peer-reviewed]
English, Scientific journal

Paraphrase Identification with Lexical, Syntactic and Sentential Encodings
Sheng Xu; Xingfa Shen; Fumiyo Fukumoto; Jiyi Li; Yoshimi Suzuki; Hiromitsu Nishizaki
Applied Sciences-Basel, 10, 12, 4144, 4144, MDPI AG, 2020, [Peer-reviewed]
English, Scientific journal, Paraphrase identification has been one of the major topics in Natural Language Processing (NLP). However, how to interpret a diversity of contexts such as lexical and semantic information within a sentence as relevant features is still an open problem. This paper addresses the problem and presents an approach for leveraging contextual features with a neural-based learning model. Our Lexical, Syntactic, and Sentential Encodings (LSSE) learning model incorporates Relational Graph Convolutional Networks (R-GCNs) to make use of different features from local contexts, i.e., word encoding, position encoding, and full dependency structures. By utilizing the hidden states obtained by the R-GCNs as well as lexical and sentential encodings by Bidirectional Encoder Representations from Transformers (BERT), our model learns the contextual similarity between sentences effectively. The experimental results by using the two benchmark datasets, Microsoft Research Paraphrase Corpus (MRPC) and Quora Question Pairs (QQP) show that the improvement compared with the baseline, BERT sentential encodings model, was 1.7% F1-score on MRPC and 1.0% F1-score on QQP. Moreover, we verified that the combination of position encoding and syntactic features contributes to performance improvement.

A Dataset of Crowdsourced Word Sequences: Collections and Answer Aggregation for Ground Truth Creation
Jiyi Li; Fumiyo Fukumoto
the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019) Workshop Aggregating and analysing crowdsourced annotations for NLP (AnnoNLP 2019), 24, 28, Nov. 2019, [Peer-reviewed]
English, International conference proceedings

Budget Cost Reduction for Label Collection with Confusability based Exploration
Jiyi Li
26th International Conference on Neural Information Processing of the Asia-Pacific Neural Network Society (ICONIP 2019), 231, 241, Nov. 2019, [Peer-reviewed]
English, International conference proceedings

Text Categorization by Learning Predominant Sense of Words as Auxiliary Task
Kazuya Shimura; Jiyi Li; Fumiyo Fukumoto
the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), 1109, 1119, Jul. 2019, [Peer-reviewed]
English, International conference proceedings

超問題：専門知識を要するクラウドソーシングタスクの回答統合法
李吉屹; 馬場雪乃; 鹿島久嗣
DBSJ Journal, 17-J, Mar. 2019, [Peer-reviewed]
Japanese, Scientific journal

HFT-CNN: Learning Hierarchical Category Structure for Multi-label Short Text Categorization
Kazuya Shimura; Jiyi Li; Fumiyo Fukumoto
the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018), 811, 816, Nov. 2018, [Peer-reviewed]
English, International conference proceedings

Incorporating Worker Similarity for Label Aggregation in Crowdsourcing
Jiyi Li; Yukino Baba; Hisashi Kashima
The 27th International Conference on Artificial Neural Networks (ICANN 2018), 596, 606, Oct. 2018, [Peer-reviewed]
English, International conference proceedings

Simultaneous Clustering and Ranking from Pairwise Comparisons
Jiyi Li; Yukino Baba; Hisashi Kashima
the 27th International Joint Conference on Artificial Intelligence (IJCAI 2018), 1554, 1560, Jul. 2018, [Peer-reviewed]
English, International conference proceedings

Hyper Questions: Unsupervised Targeting of a Few Experts in Crowdsourcing
Jiyi Li; Yukino Baba; Hisashi Kashima
Proceeding of the 26th ACM International Conference on Information and Knowledge Management (CIKM 2017), 1069, 1078, Nov. 2017, [Peer-reviewed]
English, International conference proceedings

Iterative Reduction Worker Filtering for Crowdsourced Label Aggregation
Jiyi Li; Hisashi Kashima
Proceeding of the 18th International Conference on Web Information Systems Engineering (WISE 2017), 46, 54, Oct. 2017, [Peer-reviewed]
English, International conference proceedings

Distributed Multi-task Learning for Sensor Network
Jiyi Li; Tomohiro Arai; Yukino Baba; Hisashi Kashima; Shotaro Miwa
Proceeding of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2017), 657, 672, Sep. 2017, [Peer-reviewed]
English, International conference proceedings

A Generalized Model for Multidimensional Intransitivity
Jiuding Duan; Jiyi Li; Yukino Baba; Hisashi Kashima
Proceeding of the 21st Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2017), 840, 852, May 2017, [Peer-reviewed]
English, International conference proceedings

Evaluation with Confusable Ground Truth
Jiyi Li; Masatoshi Yoshikawa
Proceeding of the Twelfth Asia Information Retrieval Societies Conference (AIRS 2016), 363, 369, Dec. 2016, [Peer-reviewed]
English, International conference proceedings

A Dynamic-Static Approach of Model Fusion for Document Similarity Computation
Jiyi Li; Yasuhito Asano; Toshiyuki Shimizu; Masatoshi Yoshikawa
Proceeding of the 16th International Conference on Web Information System Engineering (WISE 2015), 1, 16, Nov. 2015, [Peer-reviewed]
English, International conference proceedings

Reachability based Ranking in Interactive Image Retrieval
Jiyi Li
Proceeding of the 38th International ACM SIGIR conference on research and development in Information Retrieval (SIGIR 2015), 867, 870, Aug. 2015, [Peer-reviewed]
English, International conference proceedings

A Multi-Round Global Performance Evaluation Method for Interactive Image Retrieval
Jiyi Li
Proceeding of the 16th International Conference on Web-Age Information Management (WAIM 2015), 161, 168, Jun. 2015, [Peer-reviewed]
English, International conference proceedings

Document Similarity Computation by Combining Multiple Representation Models
Jiyi Li; Toshiyuki Shimizu; Masatoshi Yoshikawa
Proceeding of the 16th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD 2015), 521, 526, Jun. 2015, [Peer-reviewed]
English, International conference proceedings

Domain Specific Commonsense Relation Extraction from Bag of Concepts Metadata
Jiyi Li
Proceedings of the 9th International Conference on Ubiquitous Information Management and Communication (IMCOM (ICUIMC) 2015), 96, Jan. 2015, [Peer-reviewed]
English, International conference proceedings

Map Route Ranking with Weighted Distance using Environmental Factors
Jiyi Li
arXiv, arXiv, Apr. 2014
English

Potential Semantics in Multi-modal Relevance Feedback Information for Image Retrieval
Jiyi Li; Qiang Ma; Yasuhito Asano; Masatoshi Yoshikawa
Proceedings of the 37th Annual IEEE Computer Software and Applications Conference (COMPSAC 2013) Special Sessions on Fast Abstracts, 830, 831, Jul. 2013, [Peer-reviewed]
English, International conference proceedings

Tag Quality Improvement for Social Image Hosting Website
Jiyi Li; Qiang Ma; Yasuhito Asano; Masatoshi Yoshikawa
IPSJ Transactions on Databases (TOD), 6, 3, 177, 186, Jun. 2013, [Peer-reviewed]
English, International conference proceedings

Improving Content-based Social Image Retrieval Based on an Image-tag Relationship Model
Li Jiyi; Ma Qiang; Asano Yasuhito; Yoshikawa Masatoshi
IMT, 8, 3, 646, 654, Information and Media Technologies Editorial Board, 2013
English, With the recent rapid growth of social image hosting websites, such as Flickr, it is easier to construct a large database with social tagged images. We propose an unsupervised approach for automatic ranking social images to improve content-based social image retrieval. We construct an image-tag relationship graph model with both social images and tags. The approach extracts visual and textual information and combines them for ranking by propagating them through the graph links with an optimized mutual reinforcement process. We conduct experiments showing that our approach can successfully use social tags for ranking and improving content-based social image search results, and performs better than other approaches.

Improving Content-based Social Image Retrieval based on an Image-Tag Relationship Model
Jiyi Li; Qiang Ma; Yasuhito Asano; Masatoshi Yoshikawa
IPSJ Transactions on Databases (TOD), 5, 3, 117, 125, Sep. 2012, [Peer-reviewed]
English, Scientific journal

Improving Folksonomy Tag Quality of Social Image Hosting Websites
Jiyi Li; Qiang Ma; Yasuhito Asano; Masatoshi Yoshikawa
Proceedings of the 13th International Conference on Web-Age Information Management (WAIM 2012) workshops on Unstructured Data Management (USDM 2012), 264, 275, Aug. 2012, [Peer-reviewed]
English, International conference proceedings

Re-ranking Content-Based Social Image Search Results by Multi-modal Relevance Feedback
Jiyi Li; Qiang Ma; Yasuhito Asano; Masatoshi Yoshikawa
DBSJ Journal, 11, 1, 67, 72, 日本データベース学会, Jun. 2012, [Peer-reviewed]
English, Scientific journal

Re-ranking by Multi-modal Relevance Feedback for Content-Based Social Image Retrieval
Jiyi Li; Qiang Ma; Yasuhito Asano; Masatoshi Yoshikawa
Proceedings of the 14th Asia-Pacific Web Conference (APWeb 2012), 399, 410, Apr. 2012, [Peer-reviewed]
English, International conference proceedings

Re-ranking Content Based Social Image Search Results by Multi Modal Relevance Feedback
LI Jiyi; MA Qiang; ASANO Yasuhito; YOSHIKAWA Masatoshi
IMT, 7, 3, 1130, 1135, Information and Media Technologies Editorial Board, 2012
English, Social image hosting websites, such as Flickr, have a rapid growth recently. Content based image retrieval on such websites is an useful potential service but is still unavailable because its performance is unsatisfactory. We propose a multi modal relevance feedback (MMRF) scheme and a supervised re-ranking approach based on it to improve the performance for practical application. Our multi modal scheme utilizes both image and social tag relevance feedback instances. The approach propagates visual and textual information as well as multi modal relevance feedback information on the graph with a mutual reinforcement process. We conduct experiments based on real world data from Flickr to evaluate the performance of our approach. We also conduct an experiment to show that our multi modal relevance feedback scheme significantly improves performance compared with traditional single modal relevance feedback (SMRF) scheme.

Ranking Content-Based Social Images Search Results with Social Tags
Jiyi Li; Qiang Ma; Yasuhito Asano; Masatoshi Yoshikawa
Proceedings of the Seventh Asia Information Retrieval Societies Conference (AIRS 2011), 147, 156, Dec. 2011, [Peer-reviewed]
English, International conference proceedings

Context-based image re-ranking for content-based image retrieval
Jiyi Li
Proceedings of the 2011 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP 2011), 39, 46, Apr. 2011, [Peer-reviewed]
English, International conference proceedings

The Research on Offline Palmprint Identification
Jiyi Li; Guangshun Shi; Yan Zheng; Yuanfang Liu
Proceedings of the 2009 WRI World Congress on Computer Science and Information Engineering (CSIE'09), 587, 590, Mar. 2009, [Peer-reviewed]
English, International conference proceedings

A Novel Palmprint Feature Processing Method based on Skeleton Image
Jiyi Li; Guangshun Shi
Proceedings of the 2008 IEEE International Conference on Signal Image Technology and Internet Based Systems - Volume 00 (SITIS'08), 221, 228, Nov. 2008, [Peer-reviewed]
English, International conference proceedings

Segmentation of Offline Palmprint
Yan Zheng; Yuanfang Liu; Guangshun Shi; Jiyi Li; Qingren Wang
Proceedings of the 2007 Third international IEEE Conference on Signal-Image Technologies and internet-Based System - Volume 00 (SITIS'07), 804, 811, Dec. 2007, [Peer-reviewed]
English, International conference proceedings

Automatic performance evaluation of palmprint recognition (In Chinese)
Zhenyu Qi; Jing Xu; Jiyi Li; Guangshun Shi
Computer Engineering and Applications, 43, 28, 214, 216, Dec. 2007, [Peer-reviewed]
Chinese, International conference proceedings

A New Point Pattern Matching Method for Palmprint
Jiyi Li; Guangshun Shi; Qiu Feng; Hongwu Wan
Proceedings of the 2007 International Conference on Artificial Intelligence and Pattern Recognition (AIPR-07), 302, 306, Jul. 2007, [Peer-reviewed]
English, International conference proceedings

■ Lectures, oral presentations, etc.

低リソースの意見要約のための教師なしドメイン適応
小杉宥斗; 李吉屹; 福本文代
言語処理学会第28回年次大会(NLP2022), Mar. 2022, Japanese, Oral presentation
[Domestic Conference]

局所および大域的特徴量に基づく語義の曖昧性解消
浅川翔; 鈴木良弥; 李吉屹; 福本文代
言語処理学会第28回年次大会 (NLP2022), Mar. 2022, Japanese, Oral presentation
[Domestic Conference]

リフレーミングキーボードによるユーザの主観的幸福度の向上
李紀飛; 郷健太郎; 木下雄一朗; 李吉屹; 福本文代
第23回日本感性工学会大会, Sep. 2021, Japanese, Oral presentation
[Domestic Conference]

画像におけるゲームによる多様・信頼的・効率的な感情アノテーション
左幸坤; 李吉屹; 茅暁陽
The 13th Forum on Data Engineering and Information Management (DEIM2021), Mar. 2021, Japanese, Oral presentation
[Domestic Conference]

Fine-tuningに基づくショートテキストの自動分類
志村和也; 李吉屹; 福本文代
信学技報第13回テキストアナリティクス・シンポジウム, Sep. 2018, Japanese, Oral presentation
[Domestic Conference]

超問題: 専門知識を要するクラウドソーシングタスクの回答統合法
李吉屹; 馬場雪乃; 鹿島久嗣
第10回データ工学と情報マネジメントに関するフォーラム (DEIM2018), Mar. 2018, Japanese, Oral presentation
[Domestic Conference]

A Generalized Model for Multi-dimensional Intransitivity
Jiuding Duan; Jiyi Li; Yukino Baba; Hisashi Kashima
The 19th Information-Based Indection Sciences Workshop (IBIS2016), Nov. 2016, English, Oral presentation
[Domestic Conference]

The effort in DIAS toward sharing earth science data by metadata management
Toshiyuki Shimizu; Masafumi Ono; Asanobu Kitamoto; Hiroko Kinutani; Kaori Kuroiwa; Nakahara Yoko; Satoko Miura; Masatoshi Yoshikawa; Jiyi Li
Japan Geoscience Union (JpGU), May 2015, English, Oral presentation
[International presentation]

Improving Document Similarity Computation by Model Performance Prediction
Jiyi Li; Toshiyuki Shimizu; Yasuhito Asano; Masatoshi Yoshikawa
The 7th Forum on Data Engineering and Information Management (DEIM2015), Mar. 2015, English, Oral presentation
[Domestic Conference]

DIAS Data Release and the Cooperation Among Data Centers by Metadata
Hiroko Kinutani; Toshiyuki Shimizu; Jiyi Li; Masatoshi Yoshikawa
Asia Oceania Geosciences Society (AOGS), Aug. 2014, English, Oral presentation
[International presentation]

Development of DIAS Metadata System
Masatoshi Yoshikawa; Toshiyuki Shimizu; Jiyi Li; Yoko Nakahara; Hiroko Kinutani
Japan Geoscience Union (JpGU), May 2014, English, Oral presentation
[International presentation]

The Data Release of Earth Observation Project Data Products Considering Data Provider’s Policies by DIAS
Hiroko Kinutani; Toshiyuki Shimizu; Jiyi Li; Yoko Nakahara; Masatoshi Yoshikawa; Masaru Kitsuregawa; Toshio Koike
Japan Geoscience Union (JpGU), May 2014, English, Oral presentation
[International presentation]

Semantic Knowledge Base Construction from Domain-Specified Metadata
Jiyi Li; Toshiyuki Shimizu; Masatoshi Yoshikawa
The 6th Forum on Data Engineering and Information Management (DEIM2014), Mar. 2014, English, Oral presentation
[Domestic Conference]

Multi Modal Relevance Feedback for Content Based Social Image Retrieval
Jiyi Li; Qiang Ma; Yasuhito Asano; Masatoshi Yoshikawa
iDB Workshop 2013, Jul. 2013, English, Oral presentation
[International presentation]

User Intention in Image Retrieval and Small-Granularity Query Topic Intention Detection
Jiyi Li; Qiang Ma; Yasuhito Asano; Masatoshi Yoshikawa
The 6th Forum on Data Engineering and Information Management (DEIM 2013), Mar. 2013, English, Oral presentation
[Domestic Conference]

■ Research Themes

Effect of sentiment conversion in future vision-based design
Grants-in-Aid for Scientific Research
01 Apr. 2024 - 31 Mar. 2027
郷健太郎; 李吉屹; 福本文代; 木下雄一朗
Japan Society for the Promotion of Science, Grant-in-Aid for Scientific Research (C), University of Yamanashi, 24K15633

Learning Reliable Deep Models from Noise Labels by Crowdsourcing
Grants-in-Aid for Scientific Research
01 Apr. 2023 - 31 Mar. 2027
李吉屹; 福本文代; 鈴木良弥
Japan Society for the Promotion of Science, Grant-in-Aid for Scientific Research (B), University of Yamanashi, 23K28092

ポジティブキーボード：文字入力によるウェルビーイングへの新たな介入の試み
01 Apr. 2020 - 31 Mar. 2023
郷健太郎
本研究は, クラウドソーシングサービスを利用した大規模データへの高精度ラベル付与タスクにおいて, ラベル付与が必要なデータとワーカーの特質に着目することにより, サービス利用時のコストを抑えることが可能な機械学習法を提案する. 本研究は, 大規模データと多数のラベルを対象としたラベル付与においてトレードオフの関係にあるコスト削減と品質向上を同時に目指す点が挑戦的であり, 独自性がある. 本研究の成果は, 近年脚光を浴びている深層学習などの教師付き機械学習において本質的な問題である学習データの作成に直接貢献することから, 産業界における多様な分野での人工知能技術の実用化と進展が期待できる.
科学研究費補助金（基盤研究(C)）, Competitive research funding

クラウドソーシングによるコスト削減のため機械学習法
01 Apr. 2019 - 31 Mar. 2022
李吉屹
本研究は, クラウドソーシングサービスを利用した大規模スパースなデータへの高精度ラベル付与タスクにおいて, ラベル付与が必要なデータとワーカーの特質に着目することにより, サービス利用時のコストを抑えることが可能な機械学習法を提案する．大規模データと多数のラベルを対象としたラベル付与作業においてトレードオフの関係にあるコスト削減と品質向上を同時に目指す点が挑戦的であり, 独自性がある. 本研究の成果は, 近年脚光を浴びている深層学習などの教師付き機械学習において本質的な問題である学習データの作成に直接貢献することから, 産業界における多様な分野での人工知能技術の実用化と進展が期待できる.
科学研究費補助金（若手研究）, Competitive research funding

マルチタスク学習による論文の採否自動判定
01 Apr. 2019 - 31 Mar. 2022
李吉屹
質の高い論文を短期間で公開するためには，論文投稿前の著者への支援と同時に，査読者の労力を極力軽減することが必須である．本研究は，学術論文の採否判定を新規性や明瞭性など複数の評価項目から成るマルチタスクと仮定し，アテンション機構によるCNNを用いたマルチタスク学習により論文の採否を自動的に判定するシステムを開発する
財団法人KDDI財団, 調査研究助成, Competitive research funding

山梨大学若手表彰
若手表彰
01 Nov. 2019 - 31 Mar. 2020
李吉屹
山梨大学, Competitive research funding

実データからのマイニング，解析技術に関する研究交流
日本・アジア青少年サイエンス交流事業（さくらサイエンスプラン）
01 Nov. 2018 - 31 Mar. 2019
インターネットの急速な普及により，多数のアプリケーションを用い，ウェブ・ソースから膨大な量の情報を自動的，かつ容易に収集することが可能となった．このことを背景に，近年，データマイニング，検索，及び解析技術に関する社会からの要請は，急速に増している．一方で，データの解析はそのデータが利用されている社会や文化的背景を無視し記号列として解析されることが多いため，正しく解析できず，結果的に実用的な知識として使用できない問題が生じている．本研究交流では，南開大学が実施している理論に基づくデータ解析法，及び山梨大学が実施している実データに基づく解析技術に関する学生間の研究交流を通し，将来的にデータ解析において若い世代が国際的に活躍できる優秀な人材の育成に努めることを目的とする．
JST, Competitive research funding

Reachability based Ranking in Interactive Image Retrieval
研究者海外派遣助成
01 Jul. 2015 - 31 Mar. 2016
公益財団法人情報科学国際交流財団, Competitive research funding

Ranking Content-Based Social Images Search Results with Social Tags
国際会議論文発表者助成
Dec. 2011 - Apr. 2012
公益財団法人NEC C&C財団, Competitive research funding

SEARCH

Li Jiyi

Faculty of Information Science and Technology Computer Science and Information Technology Knowledge Software ScienceAssociate Professor

Researcher basic information

Career

Research activity information

Faculty of Information Science and Technology　Computer Science and Information Technology　Knowledge Software Science Associate Professor