Jong-Hoon Oh@NICT | データ駆動知能システム研究センター

Jong-Hoon Oh (呉鍾勲)

（国研）情報通信研究機構(NICT)
ユニバーサルコミュニケーション研究所
データ駆動知能システム研究センター上席研究員

博士（工学）

rovellia at_mark_here nict.go.jp

Research Interests

Question Answering
Knowledge Discovery from the Web
Information Retrieval & Text Processing
Machine Transliteration

Short Bio.

I have been working in NICT as an expert researcher since Oct. 2005. I was involved in the "Japanese-Chinese machine translation project" and charge of unknown word translation including machine transliteration. Since 2008, I had been working on knowledge acquisition from Wikipedia, especially for acquisition of multilingual semantic knowledge such as hyponymy relations. I am currently interested in non-factoid question answering using semantic knowledge.

Selected Publications (Full list)

Jong-Hoon Oh, Ryu Iida, Julien Kloetzer, Kentaro Torisawa, BERTAC: Enhancing Transformer-based Language Models with Adversarially Pretrained Convolutional Neural Networks, In the Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021), pp. 2103–2115, Bangkok, Thailand, August, 2021. [GitHub]
Kento Sugimoto, Toshihiro Takeda, Jong-Hoon Oh, Shoya Wada, Shozo Konishi, Asuka Yamahata, Shiro Manabe, Noriyuki Tomiyama, Takashi Matsunaga, Katsuyuki Nakanishi, Yasushi Matsumura, 2021, Extracting clinical terms from radiology reports with deep learning, Journal of Biomedical Informatics. Vol 116
Kazuma Kadowaki, Ryu Iida, Kentaro Torisawa, Jong-Hoon Oh and Julien Kloetzer, Event Causality Recognition Exploiting Multiple Annotators’ Judgments and Background Knowledge, In the Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019), pp.5820--5826, Hong Kong, China, November, 2019.
Jong-Hoon Oh, Kazuma Kadowaki, Julien Kloetzer, Ryu Iida and Kentaro Torisawa, Open Domain Why-Question Answering with Adversarial Learning to Encode Answer Texts, In the Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), pp.4227--4237, Florence, Italy, July, 2019.
Ryu Iida, Canasai Kruengkrai, Ryo Ishida, Kentaro Torisawa, Jong-Hoon Oh and Julien Kloetzer, Exploiting Background Knowledge in Compact Answer Generation for Why-questions, In the Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI 2019), pp.142--151, Honolulu, Hawai, USA, January, 2019.
Ryo Ishida, Kentaro Torisawa, Jong-Hoon Oh, Ryu Iida, Canasai Kruengkrai and Julien Kloetzer, Semi-Distantly Supervised Neural Model for Generating Compact Answers to Open-Domain Why Questions, In the Proceedings of 32nd AAAI Conference on Artificial Intelligence (AAAI 2018), pp.5803--5811, New Orleans, Louisiana, USA, February, 2018.
Canasai Kruengkrai, Kentaro Torisawa, Chikara Hashimoto, Julien Kloetzer, Jong-Hoon Oh and Masahiro Tanaka Improving Event Causality Recognition with Multiple Background Knowledge Sources using Multi-Column Convolutional Neural Networks In the Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI-17), pp. 3466-3473
Jong-Hoon Oh, Kentaro Torisawa, Canasai Kruengkrai, Ryu Iida and Julien Kloetzer, Multi-column Convolutional Neural Networks with Causality-Attention for Why-Question Answering In the Proceedings of The tenth ACM International Conference on Web Search and Data Mining (WSDM2017), pp.415-424
Junta Mizuno, Masahiro Tanaka, Kiyonori Ohtake, Jong-Hoon Oh, Julien Kloetzer, Chikara Hashimoto and Kentaro Torisawa WISDOM X, DISAANA and D-SUMM: Large-scale NLP Systems for Analyzing Textual Big Data In the Proceedings of the 26th International Conference on Computational Linguistics (COLING 2016) (Demo Track), pp.263-267
Ryu Iida, Kentaro Torisawa, Jong-Hoon Oh, Canasai Kruengkrai and Julien Kloetzer Intra-Sentential Subject Zero Anaphora Resolution using Multi-Column Convolutional Neural Network In the Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2016), pp.1244--1254, Austin, Texas, USA, November, 2016
Jong-Hoon Oh, Kentaro Torisawa, Chikara Hashimoto, Ryu Iida, Masahiro Tanaka and Julien Kloetzer, A Semi-Supervised Learning Approach to Why-Question Answering, In the Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI-16), pp.3022--3029, Phoenix, USA, Feb, 2016
Julien Kloetzer, Kentaro Torisawa, Chikara Hashimoto, Jong-Hoon Oh, Large-Scale Acquisition of Entailment Pattern Pairs by Exploiting Transitivity, In the Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2015), pp.1649--1655, Lisbon, Portugal, September, 2015
Ryu Iida, Kentaro Torisawa, Chikara Hashimoto, Jong-Hoon Oh, Julien Kloetzer, Intra-sentential Zero Anaphora Resolution using Subject Sharing Recognition, In the Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2015), pp.2179--2189, Lisbon, Portugal, September, 2015
Chikara Hashimoto, Kentaro Torisawa, Julien Kloetzer and Jong-Hoon Oh, Generating Event Causality Hypotheses through Semantic Relations, In the Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI-15), pp.2396--2403, Austin, Texas, USA, January, 2015
Motoki Sano, Kentaro Torisawa, Julien Kloetzer, Chikara Hashimoto, Istvan Varga and Jong-Hoon Oh, Million-scale Derivation of Semantic Relations from a Manually Constructed Predicate Taxonomy, In the Proceedings of the 25th International Conference on Computational Linguistics (COLING 2014), pp.1423-1434, Dublin, Ireland, August, 2014.
Chikara Hashimoto, Kentaro Torisawa, Julien Kloetzer, Motoki Sano, Istvan Varga, Jong-Hoon Oh and Yutaka Kidawara, Toward Future Scenario Generation: Extracting Event Causality Exploiting Semantic Relation, Context, and Association Features, In the Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL 2014), pp.987-997, Baltimore, Maryland, USA, June, 2014.
Julien Kloetzer, Stijn De Saeger, Kentaro Torisawa, Chikara Hashimoto, Jong-Hoon Oh, Motoki Sano and Kiyonori Ohtake. Two-stage Method for Large-scale Acquisition of Contradiction Pattern Pairs using Entailment, In Proceedings of EMNLP 2013: Conference on Empirical Methods in Natural Language Processing and Natural Language Learning, Poster, Seattle, USA, October, 2013
Jong-Hoon Oh, Kentaro Torisawa, Chikara Hashimoto, Motoki Sano, Stijn De Saeger and Kiyonori Ohtake. Why-Question Answering using Intra- and Inter-Sentential Causal Relations, In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013), pp. 1733--1743, Sofia, Bulgaria, August, 2013.
Istvan Varga, Motoki Sano, Kentaro Torisawa, Chikara Hashimoto, Kiyonori Ohtake, Takao Kawai, Jong-Hoon Oh and Stijn De Saeger. Aid is Out There: Looking for Help from Tweets during a Large Scale Disaster, In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013), pp.1619--1629, Sofia, Bulgaria, August, 2013.
意味的極性と単語クラスを用いたWhy型質問応答の改善, 呉鍾勲、鳥澤健太郎、橋本力、川田拓也、Stijn De Saeger、風間淳一、王軼謳、情報処理学会論文誌,Vol. 54(7), pp.1951-1966, 2013.
Jong-Hoon Oh, Kentaro Torisawa, Chikara Hashimoto, Takuya Kawada, Stijn De Saeger, Junichi Kazama and Yiou Wang. Why Question Answering using Sentiment Analysis and Word Classes, Proceedings of EMNLP-CoNLL 2012: Conference on Empirical Methods in Natural Language Processing and Natural Language Learning, Oral, pp.368--378. 2012. 7.
Chikara Hashimoto, Kentaro Torisawa, Stijn De Saeger, Jong-Hoon Oh, and Jun'ichi Kazama. Excitatory or Inhibitory: A New Semantic Orientation Extracts Contradiction and Causality from the Web, Proceedings of EMNLP-CoNLL 2012: Conference on Empirical Methods in Natural Language Processing and Natural Language Learning, Poster, pp.619--630. 2012. 7.
Wikipediaを利用した上位下位関係の詳細化, 山田一郎、橋本力、呉鍾勲、鳥澤健太郎、黒田航、デサーガステイン、土田正明、風間淳一, 自然言語処理, March 2012
Co-STAR:上位下位関係獲得のための共訓練アルゴリズム, 呉鍾勲、山田一郎、鳥澤健太郎、Stijn De Saeger、橋本力, 情報処理学会論文誌, December 2011.
言語横断共訓練による単語間の上位下位関係の獲得, 呉鍾勲、山田一郎、内元清貴、鳥澤健太郎、橋本力, 情報処理学会論文誌, December 2011.
Ichiro Yamada, Jong-Hoon Oh, Chikara Hashimoto, Kentaro Torisawa, Jun'ichi Kazama, Stijn De Saeger and Takuya Kawada, Extending WordNet with Hypernyms and Siblings Acquired from Wikipedia, In Proceedings of the 5th International Joint Conference on Natural Language Processing, pp. 874--882, Chiang Mai, Thailand, November, 2011.
Stijn De Saeger, Kentaro Torisawa, Masaaki Tsuchida, Jun’ichi Kazama, Chikara Hashimoto, Ichiro Yamada, Jong-Hoon Oh, Istvan Varga, Yulan Yan, Relation Acquisition using Word Classes and Partial Patterns, Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2011) Jul 2011
Jong-Hoon Oh, Ichiro Yamada, Kentaro Torisawa, and Stijn De Saeger, 2010, Co-STAR: A Co-Training Style Algorithm for Hyponymy Relation Acquisition from Structured and Unstructured Text, International Conference on Computational Linguistics (COLING 2010), pp. 842—850, Beijing, China, August 2010
- Errata: By mistake, we did not write "L^(i+1)_S := L^i_S" and "L^(i+1)_U := L^i_U" between lines 8 and 9 in Figure 2 (the pseudo code of our Co-STAR algorithm). Please see the details here (errata and modification page). The revised version of this paper is here (pdf).
Jong-Hoon Oh, Kiyotaka Uchimoto and Kentaro Torisawa, 2009, Bilingual Co-Training for Monolingual Hyponymy-Relation Acquisition, ACL-IJCNLP' 09
Jong-Hoon Oh, Kiyotaka Uchimoto and Kentaro Torisawa, 2009, Can Chinese Phonemes Improve Machine Transliteration?: A Comparative Study of English-to-Chinese Transliteration Models, EMNLP 2009, Conference on Empirical Methods in Natural Language Processing

Selected Awards

ドコモ・モバイル・サイエンス賞先端技術部門優秀賞, 2015年10月
ALAGIN & NLP 若手の会合同シンポジウム奨励賞, 2013年9月