Page 156 - My FlipBook
P. 156
研
人 Associate Research Fellow
員 古倫維 Lun-Wei Ku
Faculty Ph.D., Computer Science and Information Engineering,
National Taiwan Univeristy, Taiwan
T +886-2-2788-3799 ext. 1808 E lwku@iis.sinica.edu.tw
F +886-2-2782-4814 W www.lunweiku.com/
・ Assistant & Associate Research Fellow, Institute of Information Science, Academia Sinica
(2012-present)
・ Assistant & Associate Professor, National Chiao Tung University (2017-present)
・ Secretary-General, Association for Computational Linguistics and Chinese Language
Processing (2015-present)
・ Information O cer, ACL-SIGHAN (2016-present)
・ AFNLP Executive Committee Members-at-Large (MAL), (2016-2018)
Research Description
My research interests lie in subjective information processing, specifically sentiment analysis and opinion mining, which is a subarea of
natural language processing (NLP), and its interplay with knowledge inference (AI) and computer human interaction (CHI). I am most
interested in understanding how the subjective information such as emotions, opinions, lies, and sarcasm expressed or perceived by people,
aroused by content, and inferred in events, especially through text media. In addition, I pay attention to the utilization of knowledge for
better understanding and downstream applications. In the past, I have developed the well-known popular Chinese sentiment analysis tool
CSentiPackage, which includes sentiment dictionaries, labeled resources, the scoring module, and the deep learning model. On top of these
useful materials, my lab has developed technologies such as the state of the art stance classi cation model UTCNN, the emotion noti cation
system for social media EmotionPush, the reading preference guided article recommendation system PGA, and the knowledge enriched
visual storytelling model KG-Story. I organized previously NTCIR MOAT and currently EmotionX sentiment research challenges which attract
researchers in my area to work on important topics together. Toward the goal of leveraging subjective information analysis techniques to
improve the quality of life, I am working on several foundational topics in natural language understanding, such as semantic role labeling
and sentence parsing, as well as many advanced topics including smart distance supervision, multi-modal content generation, lie detection,
knowledge-based co-training, long inference, fake news intervention, and human-like agent construction.
Publications 6. Chieh-Yang Huang, Mei-Hua Chen and Lun-Wei Ku, "Towards
a Better Learning of Near-Synonyms: Automatically Suggesting
1. Chao-Chun Hsu, Zi-Yuan Chen, Chi-Yang Hsu, Chih-Chia Li, Example Sentences via Filling in the Blank," In Proceedings of
Tzu-Yuan Lin, Ting-Hao Huang, Lun-Wei Ku, "Knowledge- the 26th International World Wide Web Conference (WWW 2017),
Enriched Visual Storytelling," In Proceedings of the Thirty- Digital Learning Track.
Fourth AAAI Conference on Artificial Intelligence (AAAI 2020),
February 7 - 12, 2020, New York, USA. 7. Wei-Chung Wang and Lun-Wei Ku, "Enabling Transitivity for
Lexical Inference on Chinese Verbs Using Probabilistic Soft
2. YunZhu Song, Hong-Han Shuai, Sung-Lin Yeh, Yi-Lun Wu, Lun- Logic," Proceedings of the 8th International Joint Conference on
Wei Ku, Wen-Chih Peng, "Attractive or Faithful? Popularity- Natural Language Processing (IJCNLP 2017), December 2017.
Reinforced Learning for Inspired Headline Generation," In
Proceedings of the Thirty-Fourth AAAI Conference on Artificial 8. Wei-Fan Chen and Lun-Wei Ku, "UTCNN: a Deep Learning
Intelligence (AAAI 2020) , February 7 - 12, 2020, New York, Model of Stance Classification on Social Media Text," The 26th
USA. International Conference on Computational Linguistics (COLING
2016), December 2016.
3. Chia-Wei Chen, Sheng-Chuan Chou, Chang-You Tai and
Lun-Wei Ku, "PGA: Phrase-Guided Attention Web Article 9. Ku, Lun-Wei and Chen, Hsin-Hsi, "Mining Opinions from the
Recommendation for Next Clicks and Views," The IEEE/ACM Web: Beyond Relevance Retrieval," Journal of American Society
International Conference on Social Networks Analysis and for Information Science and Technology, volume 58, number 12,
Mining (ASONAM 2019), August 2019. pages 1838-1850, August 2007, Special Issue on Mining Web
Resources for Enhancing Information Retrieval
4. Zi-Yuan Chen, Chih-Hung Chang, Yi-Pei Chen, Jijnasa Nayak
and Lun-Wei Ku, "UHop: An Unrestricted-Hop Relation 10. Ku, Lun-Wei, Liang, Yu-Ting and Chen, Hsin-Hsi, "Opinion
Extraction Framework for Knowledge-Based Question Extraction, Summarization and Tracking in News and Blog
Answering," Proceedings of 2019 Annual Conference of the Corpora," Proceedings of AAAI-2006 Spring Symposium
North American Chapter of the Association for Computational on Computational Approaches to Analyzing Weblogs, AAAI
Linguistics (NAACL 2019), June 2019. Technical Report SS-06-03, pages 100-107, March 2006
5. Wei-Fan Chen and Lun-Wei Ku, "We Like, We Post: A Joint
User-Post Approach for Facebook Post Stance Labeling," IEEE
Transactions on Knowledge and Data Engineering, volume 30,
number 10, pages 2013-2023, October 2018.
154
人 Associate Research Fellow
員 古倫維 Lun-Wei Ku
Faculty Ph.D., Computer Science and Information Engineering,
National Taiwan Univeristy, Taiwan
T +886-2-2788-3799 ext. 1808 E lwku@iis.sinica.edu.tw
F +886-2-2782-4814 W www.lunweiku.com/
・ Assistant & Associate Research Fellow, Institute of Information Science, Academia Sinica
(2012-present)
・ Assistant & Associate Professor, National Chiao Tung University (2017-present)
・ Secretary-General, Association for Computational Linguistics and Chinese Language
Processing (2015-present)
・ Information O cer, ACL-SIGHAN (2016-present)
・ AFNLP Executive Committee Members-at-Large (MAL), (2016-2018)
Research Description
My research interests lie in subjective information processing, specifically sentiment analysis and opinion mining, which is a subarea of
natural language processing (NLP), and its interplay with knowledge inference (AI) and computer human interaction (CHI). I am most
interested in understanding how the subjective information such as emotions, opinions, lies, and sarcasm expressed or perceived by people,
aroused by content, and inferred in events, especially through text media. In addition, I pay attention to the utilization of knowledge for
better understanding and downstream applications. In the past, I have developed the well-known popular Chinese sentiment analysis tool
CSentiPackage, which includes sentiment dictionaries, labeled resources, the scoring module, and the deep learning model. On top of these
useful materials, my lab has developed technologies such as the state of the art stance classi cation model UTCNN, the emotion noti cation
system for social media EmotionPush, the reading preference guided article recommendation system PGA, and the knowledge enriched
visual storytelling model KG-Story. I organized previously NTCIR MOAT and currently EmotionX sentiment research challenges which attract
researchers in my area to work on important topics together. Toward the goal of leveraging subjective information analysis techniques to
improve the quality of life, I am working on several foundational topics in natural language understanding, such as semantic role labeling
and sentence parsing, as well as many advanced topics including smart distance supervision, multi-modal content generation, lie detection,
knowledge-based co-training, long inference, fake news intervention, and human-like agent construction.
Publications 6. Chieh-Yang Huang, Mei-Hua Chen and Lun-Wei Ku, "Towards
a Better Learning of Near-Synonyms: Automatically Suggesting
1. Chao-Chun Hsu, Zi-Yuan Chen, Chi-Yang Hsu, Chih-Chia Li, Example Sentences via Filling in the Blank," In Proceedings of
Tzu-Yuan Lin, Ting-Hao Huang, Lun-Wei Ku, "Knowledge- the 26th International World Wide Web Conference (WWW 2017),
Enriched Visual Storytelling," In Proceedings of the Thirty- Digital Learning Track.
Fourth AAAI Conference on Artificial Intelligence (AAAI 2020),
February 7 - 12, 2020, New York, USA. 7. Wei-Chung Wang and Lun-Wei Ku, "Enabling Transitivity for
Lexical Inference on Chinese Verbs Using Probabilistic Soft
2. YunZhu Song, Hong-Han Shuai, Sung-Lin Yeh, Yi-Lun Wu, Lun- Logic," Proceedings of the 8th International Joint Conference on
Wei Ku, Wen-Chih Peng, "Attractive or Faithful? Popularity- Natural Language Processing (IJCNLP 2017), December 2017.
Reinforced Learning for Inspired Headline Generation," In
Proceedings of the Thirty-Fourth AAAI Conference on Artificial 8. Wei-Fan Chen and Lun-Wei Ku, "UTCNN: a Deep Learning
Intelligence (AAAI 2020) , February 7 - 12, 2020, New York, Model of Stance Classification on Social Media Text," The 26th
USA. International Conference on Computational Linguistics (COLING
2016), December 2016.
3. Chia-Wei Chen, Sheng-Chuan Chou, Chang-You Tai and
Lun-Wei Ku, "PGA: Phrase-Guided Attention Web Article 9. Ku, Lun-Wei and Chen, Hsin-Hsi, "Mining Opinions from the
Recommendation for Next Clicks and Views," The IEEE/ACM Web: Beyond Relevance Retrieval," Journal of American Society
International Conference on Social Networks Analysis and for Information Science and Technology, volume 58, number 12,
Mining (ASONAM 2019), August 2019. pages 1838-1850, August 2007, Special Issue on Mining Web
Resources for Enhancing Information Retrieval
4. Zi-Yuan Chen, Chih-Hung Chang, Yi-Pei Chen, Jijnasa Nayak
and Lun-Wei Ku, "UHop: An Unrestricted-Hop Relation 10. Ku, Lun-Wei, Liang, Yu-Ting and Chen, Hsin-Hsi, "Opinion
Extraction Framework for Knowledge-Based Question Extraction, Summarization and Tracking in News and Blog
Answering," Proceedings of 2019 Annual Conference of the Corpora," Proceedings of AAAI-2006 Spring Symposium
North American Chapter of the Association for Computational on Computational Approaches to Analyzing Weblogs, AAAI
Linguistics (NAACL 2019), June 2019. Technical Report SS-06-03, pages 100-107, March 2006
5. Wei-Fan Chen and Lun-Wei Ku, "We Like, We Post: A Joint
User-Post Approach for Facebook Post Stance Labeling," IEEE
Transactions on Knowledge and Data Engineering, volume 30,
number 10, pages 2013-2023, October 2018.
154
