Jun Suzuki

Full Professor at Center for Data-driven Science and Artificial Intelligence (CDS) Tohoku University,
and Visiting Researcher at Google (under the cross-appointment agreement)

Bio: From April 2001 to March 2018, I was a researcher at NTT Communication Science Laboratories, NTT Corporation.
I completed a PhD in engineering from the Graduate School of Information Science, Nara Institute of Science and Technology (Matsumoto Lab.) in March 2005.
I was also a visiting researcher at CSAIL, MIT from October 2008 to October 2009 for a collaborative research with Professor Michael Collins.
I joined Tohoku University in April 2018, as an associate professor of Graduate school of Information Science (GSIS), Inui-Suzuki Laboratory.
From April 2018 to March 2020, I was also a Research Professor at NTT Communication Science Laboratories.
From July 2020, I am a full professor of the Center for Data-driven Science and Artificial Intelligence at Tohoku University.
I am also a Visiting Scientist of Natural Language Understanding Team at RIKEN Center for AIP

Google, Tohoku University and I signed a contract of cross-appointment agreement, and become a Visiting Researcher at Google (Brain team) from April 2020.


News

Old news


Research Projects

Methods

  1. Machine Learning with Large-scale, Incomplete data
  2. Semantic Textual Similarity
  3. Word Embeddings
    • [ACL-2015][NAACL-2016][IJCAI-2016][NAACL-2019]
  4. (Neural) Language Modeling
    • Language models [IJCNLP-2017][EMNLP2018a][AAAI-2019a]
    • Conditional LMs (Encoder-decoder Models) [EMNLP-2016][EACL-2017][ACL-2018][COLING-2018][BlackboxNLP-2018][PACLIC-2018]

Applications

  1. Question Answering
  2. Natural Language Processing
    • Named entity recognition [ACL-2006][EMNLP-2007][ACL-2008][ACL-2011][ACL-2013][AAAI-2014[SCIDOCA-2017]
    • Dependency parsing [EMNLP-2008][ACL-2011][ACL-2013][AAAI-2014]
    • Constituency parsing [ACL-2005][ACL-2018]
    • Discourse Parsing [EMNLP-2014][ACL-2019]
  3. Machine Translation
    • Statistical machine translation [IJCNLP-2011][ACL-2016]
    • Neural machine translation [WAT-2017][Coling-2018][WMT-2018][ACL-2019]
  4. Text Summarization
    • Text Summarization
    • Neural abstractive summarization (including headline generation) [EMNLP-2016][EACL-2017b][blackboxNLP-2018][PACLIC-2018][EMNLP-2019]
  5. Grammartical Error Collection
    • [EMNLP-2019]
  6. Speech Recognition
    • [Interspeech-2014]
  7. Computer Games
    • [ACG-2017][CGW-2017]

Publications

Books

Show Detail

fig_b01 1, 坪井 祐太, 海野 裕也, 鈴木 潤.
深層学習による自然言語処理(機械学習プロフェッショナルシリーズ)
講談社サイエンティフィク, 2017/05.
[Abstract | ]

Journals

Show Detail

  • 22, Shun Kiyono, Jun Suzuki, Tomoya Mizumoto, and Kentaro Inui.
    Massive Exploration of Pseudo Data for Grammatical Error Correction
    IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), 2020/06/27. (To appear)
    [ Abstract | Bib]

  • 21, Takumi Ito, Tatsuki Kuribayashi, Hayato Kobayahsi, Ana Brassard, Masato Hagowara, Jun Suzuki, Kentaro Inui.
    Assisting Authors to Convert Raw Products into Polished Prose
    Journal of Cognitive Science (JCS), Vol.21, No.1, pp.101-137, 2020/03/06.
    [ Abstract | Bib]

  • 20, Jun Suzuki, Yoshihiko Suhara, Hiroyuki Toda, Kyosuke Nishida.
    Personalized Visited-POI Assignment to Individual Raw GPS Trajectories
    ACM Transactions on Spatial Algorithms and Systems (ACM TSAS), Vol. 5, No. 3, pp.16:1-28, 2019/09.
    [ Abstract | Bib]

  • 19, 水上直紀, 鈴木潤, 亀甲博貴, 鶴岡慶雅
    報酬が疎な環境に適した深層強化学習法
    情報処理学会論文誌, Vol. 60, No. 3, pp. 956-966, 2018/12/04.
    [ Abstract | Bib]

  • 18, Katsuhiko Hayashi, Jun Suzuki, Masaaki Nagata.
    Shift-reduce Spinal TAG Parsing with Dynamic Programming
    Transactions of the Japanese Society for Artificial Intelligence, Vol. 31, No. 2, (2016)
    [ Abstract | Bib]

  • 17, Masaaki Nishino, Jun Suzuki, Shunji Umetani, Tsutomu Hirao, and Masaaki Nagata.
    Sequence Alignment as a Set Partitioning Problem
    Journal of Natural Language Processing,  Vol. 23, No. 2, pp. 175-194, (2016), in Japanese
    [Abstract | Bib]
    西野正彬, 鈴木潤, 梅谷俊治, 平尾努, 永田昌明.
    集合分割問題に基づく系列アラインメントのモデル化
    言語処理学会論文誌, Vol. 23, No. 2, pp. 175-194, (2016)
    [Abstract:Link to JStage | Bib]

  • 16, Tsutomu Hirao, Masaaki Nishino, Yasuhisa Yoshida, Jun Suzuki, Norihito Yasuda, Masaaki Nagata.
    Summarizing a Document by Trimming a Discourse Tree
    IEEE/ACM Transaction Audio Speech and Language Processing (TASLP), Vol. 23, No. 11, pp. 2081-2092, 2015-11.
    [Abstract | Bib]

  • 15, Jun Suzuki.
    High-Performance Semi-Supervised Learning for Extremely Large Data and Features
    IIEEJ Transactions on Image Electronics and Visual Computing, Vol. 2 No. 2, pp. 122-133, 2014-12-15.
    [Abstract | Bib]

  • 14, Katsuhiko Hayashi, Katsuhito Sudoh, Hajime Tsukada, Jun Suzuki, and Masaaki Nagata.
    Incremental Word Re-Ordering and Article Generation: Its Application to Japanese-to-English Machine Translation
    Journal of Natural Language Processing, Vol. 21, No. 5, pp. 1037-1057, (2014), in Japanese
    [Abstract | Bib]
    林克彦, 須藤克仁, 塚田元, 鈴木潤, 永田昌明.
    単語並べ替えと冠詞生成の同時逐次処理法: 日英機械翻訳への応用
    言語処理学会論文誌, Vol. 21, No. 5, pp. 1037-1057, (2014)
    [Abstract | Bib]

  • 13, Masaaki Nishino, Norihito Yasuda, Tsutomu Hirao, Jun Suzuki, Masaaki Nagata.
    Lagrangian Relaxation for Scalable Text Summarization while Maximizing Multiple Objectives
    Transactions of the Japanese Society for Artificial Intelligence, Vol.28, No.5, pp.433-441, (2013)
    [Abstract | Bib]
    (reprint) Information and Media Technologies, Vol. 8, No. 4, pp. 1017-1025, (2013)
    [Abstract | Bib]

  • 12, Yoshihiko Suhara, Jun Suzuki, Seiji Susaki.
    Spam Detection Using Online Learning From Imbalanced Data with the Focus on False Positive Rate
    IPSJ Transactions on Databases (TOD), Vol. 6, No. 2, pp. 51-60, (2013), in Japanese
    [Abstract | Bib]
    数原良彦, 鈴木潤, 片岡良治.
    `不均衡データにおける偽陽性率に着目したスパム判別器のオンライン学習'.
    情報処理学会論文誌:データベース (TOD), Vol. 6, No. 2, pp. 51-60, (2013)
    [Abstract | Bib]

  • 11, Yoshihiko Suhara, Jun Suzuki, and Ryoji Kataoka.
    Robust Online Learning to Rank via Selective Pairwise Approach Based on Evaluation Measures
    Transactions of the Japanese Society for Artificial Intelligence, Vol.28, No.1, pp.22-33, (2013)
    [Abstract | Bib]
    (reprint) Information and Media Technologies, Vol. 8, No. 1, pp. 118-129, (2013)
    [Abstract | Bib]

  • 10, Hiroyuki Shindo, Tsutomu Hirao, Jun Suzuki, Akinori, Fujino, Masaaki Nagata.
    TripleEye: Mining Closed Itemsets with Minimum Length Thresholds based on Ordered Inclusion Tree
    IPSJ Transactions on Databases (TOD), Vol. 5, No. 3 pp. 15-25, (2012)
    [Abstract | Bib]

  • 9, Jun Suzuki, Hideki Isozaki, Masaaki Nagata.
    Learning High-performance Dependency Parsing Models by Large-scale Semi-supervised Learning
    IJSP Journal, Vol. 51, No. 11, pp. 1-14, (2011), in Japanese
    [Abstract | Bib]
     鈴木潤, 磯崎秀樹, 永田昌明.
    大規模データを用いた半教師あり学習による高精度係り受け解析モデルの学習
    情報処理学会論文誌. Vol. 51, No. 11, pp. 1-14, (2011)
    [Abstract | Bib]

  • 8, Jun Suzuki, Hideki Isozaki.
    Training Conditional Random Fields Based on Segment-Wise Maximum Figure-of-Merit Functions
    The IEICE Transactions (Japanese Edition), Vol. J94-D, No. 5, pp. 908-918, (2011), in Japanese
    [Abstract:Link to CiNii | Bib]
    鈴木潤, 磯崎秀樹.
    セグメント単位の評価指標最大化に基づく条件付確率場の学習
    電子情報通信学会論文誌, Vol. J94-D, No. 5, pp. 908-918, (2011)
    [Abstract:Link to CiNii | Bib]

  • 7, Tsutomu Hirao, Jun Suzuki, Hideki Isozaki.
    Automatic Summarization as a Combinatorial Optimization Problem
    Transactions of the Japanese Society for Artificial Intelligence, Vol. 24, No. 2, pp. 223-231, (2009), in Japanese
    [Abstract | Bib]
    平尾努, 鈴木潤, 磯崎秀樹.
    最 適化問題としての文書要約
    人工知能学会論文誌, Vol. 24, No. 2, pp. 223-231, (2009)
    [Abstract | Bib]

  • 6, Tsutomu Hirao, Jun Suzuki, Hideki Isozaki.
    A Syntax Free Approach for Sentence Compression
    IPSJ Transactions on Databases (TOD), Vol. 2, No. 1, pp. 1-9, (2009)
    [Abstract | Bib]
    平尾努, 鈴木潤, 磯崎秀樹.
    構文情報に依存しない文短縮手法
    情報処理学会論文誌:データベース(TOD), Vol. 2, No. 1, pp. 1-9, (2009)
    [Abstract | Bib]

  • 5, Tsutomu Hirao, Jun Suzuki, Hideki Isozaki.
    A Discriminative Sentence Compression Method as Combinatorial Optimization Problem
    Transactions of the Japanese Society for Artificial Intelligence, Vol. 22, No. 6A, pp. 574-584, (2007), in Japanese
    [Abstract | Bib]
    平尾努, 鈴木潤, 磯崎秀樹.
    識 別学習による組合せ最適化問題としての文短縮手法
    人工知能学会論文誌, Vol. 22, No. 6A, pp. 574-584, (2007)
    [Abstract | Bib]

  • 4, Tsutomu Hirao, Jun Suzuki, Hideki Isozaki, Eisaku Maeda.
    Automatic Sentence Alignment for Monolingual Corpora
    IJSP Journal, Vol. 46, No. 10, pp. 2533-2545, (2005), in Japanese
    [Abstract | Bib]
    平尾努, 鈴木潤, 磯崎秀樹, 前田英作.
    単一言語コーパスにおける文の自動対応付け手法
    情報処理学会論文誌. Vol. 46, No. 10, pp. 2533-2545, (2005)
    [Abstract | Bib]

  • 3, Jun Suzuki, Yutaka Sasaki, and Eisaku Maeda.
    Hierarchical Directed Acyclic Graph Kernel
    Systems and Computers in Japan, Vol. 37, No. 10, pp. 58-68, (2006)
    [Abstract | Bib]
    鈴木潤, 佐々木裕, 前田英作.
    階層非循環有向グラフカーネル
    電子情報通信学会論文誌, Vol. J88-D2, No. 2, pp. 230-240, (2005)
    [Abstract:Link to CiNii | Bib]

  • 2, Yutaka Sasaki, Hideki Isozaki, Jun Suzuki, Koji Kokuryou, Tsutomu Hirao, Hideto Kazawa, Eisaku Maeda.
    SAIQA-II: A Trainable Japanese QA System with SVM
    IPSJ Journal, Vol. 45, No. 2, pp. 635-646, (2004), in Japanese
    [Abstract | Bib]
    佐々木裕, 磯崎秀樹, 鈴木潤, 国領弘治, 平尾努, 賀沢秀人, 前田英作.
    SVM を用いた学習型質問応答システムSAIQA-II
    情報処理学会論文誌, Vol. 45, No. 2, pp. 635-646, (2004)
    [Abstract | Bib]

  • 1, Jun Suzuki, Yutaka Sasaki, Eisaku Maeda.
    Question Type Classification Using Word Attribute N-gram and Statistical Machine Learning
    IPSJ Journal, Vol. 44, No. 11, pp. 2839-2853, (2003), in Japanese
    [Abstract | Bib]
    鈴木潤, 佐々木裕, 前田英作.
    単語属性N-gramと統計的機械学習による質問タイプ同定
    情報処理学会論文誌, Vol. 44, No. 11, pp. 2839-2853, (2003)
    [Abstract | Bib]

(Refereed) International Conferences and Workshops

Conferences
AAAI 3 | 2014(34) | 2019(60) 2019(61) |
IJCAI 2 | 2016(40) | 2018(52) |
NIPS 2 | 2003(5) | 2005(11) |
ACL 18 | 2003(3) | 2004(7) | 2005(10) | 2006(15) | 2008(22) | 2009(24) | 2011(26) | 2013(33) | 2015(38) | 2016(41) | 2018(51) | 2019(65) 2019(66) | 2020(75) 2020(76) 2020(77) 2020(78) 2020(79) |
NAACL-HLT 2 | (2008) | (2011) | 2016(39) | 2019(62) |
EACL 2 | 2017(43) 2017(44) |
EMNLP 14 | 2007(18) 2007(19) | 2009(25) | 2013(32) | 2014(36) | 2016(42) | 2018(54) 2018(55) | 2019(69) 2019(70) 2019(71) 2019(72) | 2020(71) 2020(82) 2020(83)
Coling 4 | 2002(1) 2002(2,demo) | 2004(8) | (2006) | 2018(53) |
IJCNLP 4 | 2008(21) | (2009) | 2011(27) | (2015) | 2017(48) 2017(49) |
Interspeech 1 | 2014(35) |
ECIR 1 | 2013(30) |
ACG 1 | 2017(45) |
PACLIC 1 | 2018(58) |
LREC 1 | 2020(74) |
INLG 1 | 2019(68) |
Workshops
MSQA 1 | 2003(4) |
AAAI Symposia 1 | 2006(14) |
BigLearn 1 | 2011(28) |
DEXA 1 | 2013(29) |
CGW 1 | 2017(46) |
SIDOCA 1 | 2017(47) |
BlackbocNLP 1 | 2018(56) |
ESSP 1 | 2019(63) |
SemEval 1 | 2019(64) |
     
Evaluation Workshops
WMT 1 | 2018(57) |
WAT 2 | 2017(50) | 2019(72) |
NIST MTeval 2 | 2005(13) | 2006(17) |
IWSLT 4 | 2005(12) | 2006(16) | 2007(20) | 2008(23) |
NTCIR 2 | 2013(31) | 2014(37) |
DUC 2  | 2003(6) | 2004(9) |
BEA 1 | 2019(67) |

Show Detail



2020 (12)

Now Printing
85, Masato Mita, Shun Kiyono, Masahiro Kaneko, Jun Suzuki and Kentaro Inui
A Self-Refinement Strategy for Noise Reduction in Grammatical Error Correction
In Findings of EMNLP-2020, 2020/11.
(acceptance rate: ???/???=???%)
[Abstract | Bib | arXiv version ]

Now Printing
84, Takumi Ito, Tatsuki Kuribayashi, Masatoshi Hidaka, Jun Suzuki and Kentaro Inui
Langsmith: An Interactive Academic Text Revision System
In Proceedings of The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP-2020 System Demonstration), 2020/11.
(acceptance rate: ???/???=???%)
[Abstract | Bib | arXiv version ]

Now Printing
83, Reina Akama, Sho Yokoi, Jun Suzuki and Kentaro Inui
Filtering Noisy Dialogue Corpora by Connectivity and Content Relatedness
In Proceedings of The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP-2020), 2020/11.
(acceptance rate: ???/???=24.6%)
[Abstract | Bib | arXiv version ]

Now Printing
82, Sho Yokoi, Ryo Takahashi, Reina Akama, Jun Suzuki and Kentaro Inui
Word Rotator’s Distance
In Proceedings of The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP-2020), 2020/11.
(acceptance rate: ???/???=24.6%)
[Abstract | Bib | arXiv version ]

Now Printing
81, Takuma Kato, Kaori Abe, Hiroki Ouchi, Shumpei Miyawaki, Jun Suzuki and Kentaro Inui.
Embeddings of Label Components for Sequence Labeling: A Case Study of Fine-grained Named Entity Recognition
In Proceedings of the 58th annual meeting of the Association for Computational Linguistics: Student Research Workshop (ACL-2020-SRW), 2020/07.
(acceptance rate: 72/202=35.6%)
[Abstract | Bib | arXiv version ]

Now Printing
80, Hiroaki Funayama, Shota Sasaki, Yuichiroh Matsubayashi, Tomoya Mizumoto, Jun Suzuki, Masato Mita and Kentaro Inui.
Preventing Critical Scoring Errors in Short Answer Scoring with Confidence Estimation
In Proceedings of the 58th annual meeting of the Association for Computational Linguistics: Student Research Workshop (ACL-2020-SRW), 2020/07.
(acceptance rate: 72/202=35.6%)
[Abstract | Bib | arXiv version ]

Now Printing
79, Tatsuki Kuribayashi, Takumi Ito, Jun Suzuki and Kentaro Inui.
Language Models as an Alternative Evaluator of Word Order Hypotheses: A Case Study in Japanese
In Proceedings of the 58th annual meeting of the Association for Computational Linguistics (ACL-2020), 2020/07.
(acceptance rate: 571/2244=25.4%)
[Abstract | Bib | arXiv version ]

Now Printing
78, Shiki Sato, Reina Akama, Hiroki Ouchi, Jun Suzuki and Kentaro Inui.
Evaluating dialogue generation systems through response selection tasks
In Proceedings of the 58th annual meeting of the Association for Computational Linguistics (ACL-2020), 2020/07.
(acceptance rate: 208/1185=17.6%)
[Abstract | Bib | arXiv version ]

Now Printing
77,Masahiro Kaneko, Masato Mita, Shun Kiyono, Jun Suzuki and Kentaro Inui.
Can Encoder-Decoder Models Benefit from Pre-trained Language Representation in Grammatical Error Correction?
In Proceedings of the 58th annual meeting of the Association for Computational Linguistics (ACL-2020), 2020/07.
(acceptance rate: 208/1185=17.6%)
[Abstract | Bib | arXiv version ]

Now Printing
76, Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Ryuto Konno and Kentaro Inui.
Instance-based Learning of Span Representations: A Case Study through Named Entity Recognition
In Proceedings of the 58th annual meeting of the Association for Computational Linguistics (ACL-2020), 2020/07.
(acceptance rate: 208/1185=17.6%)
[Abstract | Bib | arXiv version ]

Now Printing
75, Ryosuke Kuwabara, Jun Suzuki and Hideki Nakayama
Single Model Ensemble using Pseudo-Tags and Distinct Vectors
In Proceedings of the 58th annual meeting of the Association for Computational Linguistics (ACL-2020), 2020/07.
(acceptance rate: 208/1185=17.6%)
[Abstract | Bib | arXiv version ]

Now Printing
74, Makoto Morishita, Jun Suzuki, Masaaki Nagata.
JParaCrawl: A Large Scale Web-Based English-Japanese Parallel Corpus
In Proceedings of the 12th International Conference on the Language Resources and Evaluation Conference (LREC-2020), 2020/04.
(acceptance rate: ???/???=???%)
[Abstract | Bib | arXiv version ]


2019 (14)

73, Makoto Morishita, Jun Suzuki, Masaaki Nagata.
NTT Neural Machine Translation Systems at WAT 2019
In Proceedings of the 6th Workshop on Asian Translation (WAT-2019), 2019/11.
[Abstract | Bib | arXiv version ]

72, Masato Hagiwara, Takumi Ito, Tatsuki Kuribayashi, Jun Suzuki and Kentaro Inui.
TEASPN: Framework and Protocol for Integrated Writing Assistance Environments
In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP-2019 Demo track), 2019/11.
(acceptance rate: ???/???=???%)
[Abstract | Bib | arXiv version ]

71, Xiaoyu Shen, Jun Suzuki, Kentaro Inui, Hui Su, Dietrich Klakow and Satoshi Sekine.
Select and Attend: Towards Controllable Content Selection in Text Generation
In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP-2019), 2019/11.
(acceptance rate: 465/1813=25.6%)
[Abstract | Bib | arXiv version ]

70, Shun Kiyono, Jun Suzuki, Masato Mita, Tomoya Mizumoto and Kentaro Inui.
An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction
In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP-2019), 2019/11.
(acceptance rate: 218/1063=20.5%)
[Abstract | Bib | arXiv version ]

69, Hiroki Ouchi, Jun Suzuki and Kentaro Inui.
Transductive Learning of Neural Language Models for Syntactic and Semantic Analysis
In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP-2019), 2019/11.
(acceptance rate: 218/1063=20.5%)
[Abstract | Bib | arXiv version ]

68, Takumi Ito, Tatsuki Kuribayashi, Hayato Kobayashi, Ana Brassard, Masato Hagiwara, Jun Suzuki and Kentaro Inui.
Diamonds in the Rough: Generating Fluent Sentences from Early-stage Drafts
In Proceedings of the 12th International Conference on Natural Language Generation (INLG-2019), 2019/10.
(acceptance rate: 73/143=51%)
[Abstract | Bib | arXiv version ]

  67, Hiroki Asano, Masato Mita, Tomoya Mizumoto, Jun Suzuki.
The AIP-Tohoku System at the BEA-2019 Shared Task
In Proceedings of the 14th Workshop on Innovative Use of NLP for Building Educational Applications (BEA-2019), 2019/08.
[Abstract | Bib | arXiv version ]

66, Motoki Sato, Jun Suzuki and Shun Kiyono.
Effective Adversarial Regularization for Neural Machine Translation
In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL-2019), pp. 204-210, 2019/07.
(acceptance rate: 213/1168=18.2%)
[Abstract | Bib | arXiv version | Code ]

65, Tatsuki Kuribayashi, Hiroki Ouchi, Naoya Inoue, Paul Reisert, Toshinori Miyoshi, Jun Suzuki, Kentaro Inui.
An Empirical Study of Span Representations in Argumentation Structure Parsing
In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL-2019), pp. 4691-4698, 2019/07.
(acceptance rate: 213/1168=18.2%)
[Abstract | Bib | arXiv version ]

64, Kazuaki Hanawa, Shota Sasaki, Hiroki Ouchi, Jun Suzuki, Kentaro Inui.
The Sally Smedley Hyperpartisan News Detector at SemEval-2019 Task 4: Learning Classifiers with Feature Combinations and Ensembling
In Proceedings of The International Workshop on Semantic Evaluation (SemEval-2019) Task 4: Hyperpartisan News Detection, 2019/06.
[Abstract | Bib | arXiv version ]

63, Hono Shirai, Naoya Inoue, Jun Suzuki, and Kentaro Inui.
Annotating with Pros and Cons of Technologies in Computer Science Papers
In Proceedings of The Workshop on extracting structured knowledge from scientific publications (ESSP), 2019/06.
(acceptance rate: ???/???=???%)
[Abstract | Bib | arXiv version ]


62, Shota Sasaki, Jun Suzuki, and Kentaro Inui.
Subword-based Compact Reconstruction of Word Embeddings
In Proceedings of the 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT-2019), 2019/06.
(acceptance rate: 281/1067=26,3%)
[Abstract | Bib | arXiv version ]

fig_c60.png
61, Shun Kiyono, Jun Suzuki, and Kentaro Inui.
Mixture of Expert/Imitator Networks: Scalable Semi-supervised Learning Framework
In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-2019), 2019/02.
(acceptance rate: 1150/7095=16.2%)
[Abstract | Bib | arXiv version ]

fig_c59.png
60, Sho Takase, Jun Suzuki, and Masaaki Nagata.
Character n-gram Embeddings to Improve RNN Language Models
In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-2019), 2019/02.
(acceptance rate: 1150/7095=16.2%)
[Abstract | Bib | arXiv version ]


2018 (8)

fig_c58.png
59, Shun Kiyono, Sho Takase, Jun Suzuki, Naoaki Okazaki, Kentaro Inui and Masaaki Nagata.
Reducing Odd Generation from Neural Headline Generation
In Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation (PACLIC32), 10 pages, 2018/12.
(acceptance rate 32.3%: oral presentation)
[Abstract | Bib | arXiv version ]

fig_c57
58, Makoto Morishita, Jun Suzuki, Masaaki Nagata.
NTT's Neural Machine Translation Systems for WMT 2018
In Proceedings of the Third Conference on Machine Translation: Shared Task Papers (WMT-2018), pp. 461-466, 2018/11.
[Abstract | Bib]

fig_c56
57, Shun Kiyono, Sho Takase, Jun Suzuki, Naoaki Okazaki, Kentaro Inui, Masaaki Nagata
Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder models
In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP-2018), pp. 74-81, 2018/11.
[Abstract | Bib]

fig_c55
56, Sho Yokoi, Sosuke Kobayashi, Kenji Fukumizu, Jun Suzuki, Kentaro Inui.
Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions
In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP-2018), pp. 1763-1775, 2018/11.
(acceptance rate: 351/1376=25.5%)
[Abstract | Bib | arXiv version | code ]

fig_c54
55, Sho Takase, Jun Suzuki, Masaaki Nagata.
Direct Output Connection for a High-Rank Language Model
In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP-2018), pp. 4599-4609, 2018/11.
(acceptance rate: 351/1376=25.5%)
[Abstract | Bib | arXiv version | code ]

fig_c53
54, Makoto Morishita, Jun Suzuki, Masaaki Nagata.
Improving Neural Machine Translation by Incorporating Hierarchical Subword Features
In Proceedings of the 27th International Conference on Computational Linguistics (COLING-2018), pp. 618--629, 2018/8.
(acceptance rate: 332/888=37.4%)
[Abstract | Bib | arXiv version | code ]

fig_c52
53, Motoki Sato, Jun Suzuki, Hiroyuki Shindo, Yuji Matsumoto.
Interpretable Adversarial Perturbation in Input Embedding Space for Text
In Proceedings of the 27th International Joint Conference on Artificial Intelligence and the 23rd European Conference on Artificial Intelligence (IJCAI-ECAI-2018), pp. 4323-4330, 2018/7.
(acceptance rate: 710/3470=20.5%)
[Abstract | Bib | arXiv version | code]

fig_c51
52, Jun Suzuki, Sho Takase, Hidetaka Kamigaito, Makoto Morishita, Masaaki Nagata,
An Empirical Study of Building a Strong Baseline for Constituency Parsing
In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL-2018), pp. 612-618, 2018/7.
 (acceptance rate: 126/526=24%)
[Abstract | Bib | code (to appear soon)]


2017 (8)

fig_c50
51, Morishita, Jun Suzuki, Masaaki Nagata.
NTT Neural Machine Translation Systems at WAT 2017
In Proceedings of the 4th Workshop on Asian Translation (WAT2017), pp. 889-94, 2017/11.
[Abstract | Bib]

fig_c49
50, Sho Takase, Jun Suzuki, and Masaaki Nagata.
Input-to-Output Gate to Improve RNN Language Models
In Proceedings of the Eighth International Joint Conference on Natural Language Processing (IJCNLP-2017), pp. 43-48, 2017/11.
[Abstract | Bib | arXiv version | code]

fig_c48
49, Itsumi Saito, Jun Suzuki, Kyosuke Nishida, Kugatsu Sadamitsu, Satoshi Kobashikawa, Ryo Masumura, Yuji Matsumoto, and Junji Tomita.
Improving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels
In Proceedings of the Eighth International Joint Conference on Natural Language Processing (IJCNLP-2017), pp. 257-262, 2017/11.
[Abstract | Bib]

No image
48, Atsuki Sawayama, Jun Suzuki, Hiroyuki Shindo, Yuji Matsumoto.
Repetitive Named Entity Recognition using Task-dependent Similarity Calculation Model
Second International Workshop on SCIentific DOCument Analysis (SCIDOCA-2017), 2017/10
[Abstract | Bib]

fig_c46
47, Hirotaka Kameko, Jun Suzuki, Naoki Mizukami, Yoshimasa Tsuruoka.
Deep Reinforcement Learning with Hidden Layers on Future States
In Proceedings of Computer Game Workshop, 2017/8.
Computer Games (Communications in Computer and Information Science, volume 818), Springer International Publishing, pp. 46–60, 2018/02/15.
[Abstract | Bib]

fig_c45
46, Naoki Mizukami, Jun Suzuki, Hirotaka Kameko, Yoshimasa Tsuruoka.
Exploration Bonuses Based on Upper Confidence Bounds for Sparse Reward Games
In Proceedings of the Fifteenth International Conference on Advances in Computer Games (ACG-2017), 2017/7.
Advances in Computer Games (Lecture Notes in Computer Science), Springer International Publishing, pp.165–175, 2017/12/22.
[Abstract | Bib]

fig_c44
45, Jun Suzuki, Masaaki Nagata.
Cutting-off Redundant Repeating Generations for Neural Abstractive Summarization
In Proceedings of the 15th European Chapter of the Association for Computational Linguistics Conference (EACL-2017), pp. 291–297, 2017/4.
(acceptance rate: 120/504=24%)
[Abstract | Bib | arXiv version]

fig_c43
44, Tsutomu Hirao, Masaaki Nishino, Jun Suzuki, Masaaki Nagata.
Enumeration of Extractive Oracle Summaries
In Proceedings of the 15th European Chapter of the Association for Computational Linguistics Conference (EACL-2017), pp. 386–396, 2017/4.
(acceptance rate: 119/442=27%)
[Abstract | Bib | arXiv version]


2016 (4)

fig_c42
43, Sho Takase, Jun Suzuki, Tsutomu Hirao, Naoaki Okazaki, Masaaki Nagata.
Neural Headline Generation on Abstract Meaning Representation
In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP-2016), pp. 1054–1059, 2016/11.
(acceptance rate: 87/400=22%)
[Abstract | Bib]

fig_c41
42, Masaaki Nishino, Jun Suzuki, Masaaki Nagata.
Phrase Table Pruning via Submodular Function Maximization
In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL-2016), pp. 406–411, 2016/8.
(acceptance rate: 97/463=22%)
[Abstract | Bib]

fig_c40
41, Jun Suzuki, Masaaki Nagata.
Learning Compact Neural Word Embeddings by Parameter Space Sharing
In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-2016), pp. 2046–2052, 2016/7.
(acceptance rate: 551/2294=24%)
[Abstract | Bib: Link to dblp]

fig_c39
40, Jun Suzuki, Masaaki Nagata.
Right-truncatable Neural Word Embeddings
In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT-2016), pp. 1145–1151, 2016/6.
(acceptance rate: 100/396=25%)
[Abstract | Bib ]


2015 (1)

fig_c38
39, Jun Suzuki, and Masaaki Nagata.
A Unified Learning Framework of Skip-Grams and Global Vectors
In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (ACL/IJCNLP 2015), pp. 186–191, 2015/7.
(acceptance rate: 145/648=22.4%)
[Abstract | Bib]


2014 (4)

Now Printing
38, Akinori Fujino, Jun Suzuki, Tsutomu Hirao, Hisashi Kurasawa and Katsuyoshi Hayashi.
SCT-D3 at the NTCIR-11 MedNLP-2 Task
In Proceedings of the 11th NTCIR Conference on Evaluation of Information Access Technologies (NTCIR-11), 2014/12.
[Abstract | Bib:Link to dblp]

fig_c36
37, Yasuhisa Yoshida, Jun Suzuki, Tsutomu Hirao, and Masaaki Nagata.
Dependency-based Discourse Parser for Single-Document Summarization
In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP-2014), pp. 1834–1839, 2014/10.
(acceptance rate: 70/252=28%)
[Abstract | Bib]

fig_c35
36, Yotaro Kubo, Jun Suzuki, Takaaki Hori, and Atsushi Nakamura.
Restructuring Output Layers of Deep Neural Networks via Minimum Risk Parameter Clustering
In Proceedings of the 15th Annual Conference of the International Speech Communication Association (Interspeech-2014), pp. 1068–1072, 2014/9.

(acceptance rate: 614/1173=52%)
[Abstract | Bib:Link to dblp]

fig_c34
35, Jun Suzuki, and Masaaki Nagata.
Fused Feature Representation Discovery for High-dimensional and Sparse Data
In Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI-2014), pp. 1593–1599, 2014/8.
(acceptance rate: 398/1406=28.3%)
[Abstract | Bib]


2013 (4)

fig_c33
34, Jun Suzuki and Masaaki Nagata.
Supervised Model Learning with Feature Grouping based on a Discrete Constraint
In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL-2013), pp. 18–23, 2013/8.
(acceptance rate: 154/624=24%)
[Abstract | Bib]

fig_c32
33, Katsuhiko Hayashi, Katsuhito Sudoh, Hajime Tsukada, Jun Suzuki, and Masaaki Nagata.
Shift-Reduce Word Reordering and Editing for Machine Translation
In Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP-2013), pp. 1382–1386, 2013/10.
(acceptance rate: 205/772=27%)
[Abstract | Bib]

Now Printing 32, Katsuhito Sudoh, Jun Suzuki, Hajime Tsukada, Masaaki Nagata, Sho Hoshino and Yusuke Miyao.
NTT-NII Statistical Machine Translation for NTCIR-10 PatentMT
In Proceedings of the 10th NTCIR Conference on Evaluation of Information Access Technologies (NTCIR-10), 2013/6.
[Abstract | Bib:Link to dblp]

Now Printing 31, Masaaki Nishino, Norihito Yasuda, Tsutomu Hirao, Jun Suzuki, and Masaaki Nagata.
Text Summarization while Maximizing Multiple Objectives with Lagrangian Relaxation
In Proceedings of European Conference on Information Retrieval (ECIR-2013), pp. 772–775, 2013.
(acceptance rate: 38/78=49%)
[Abstract | Bib]


2012 (1)

Now Printing 30, Norihito Yasuda, Masaaki Nishino, Tsutomu Hirao, Jun Suzuki, and Ryoji Kataoka.
A Query-Focused Summarization Method that Guarantees the Inclusion of Query Words
In Proceedings on the 9th International Workshop on Text-based Information Retrieval (TIR ’12) in the 23rd International Workshop on Database and Expert Systems Applications (DEXA), pp. 126–130, 2012.
[Abstract | Bib:Link to ACM Digital Library]


2011 (3)

fig_c28
29, Kevin Duh, Jun Suzuki, and Masaaki Nagata.
Distributed Learning to Rank on Streaming Data using Alternating Direction Method of Multipliers
In Proceedings of NIPS Big Learning Workshop, 2011/12.
[Abstract | Bib]

fig_c27
28, Jun Suzuki, Kevin Duh, and Masaaki Nagata.
Distributed Minimum Error Rate Training of SMT using Particle Swarm Optimization
In Proceedings of the 5th International Joint Conference on Natural Language Processing (IJCNLP-2011), pp. 649–657, 2011/11.
(acceptance rate: 176/478=36%)
[Abstract | Bib]

fig_c26
27, Jun Suzuki, Hideki Isozaki, and Masaaki Nagata.
Learning Condensed Feature Representations from Large Unsupervised Data Sets for Supervised Learning
In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT-2011), pp. 636–641, 2011/6.
(acceptance rate: 128/512=25%)
[Abstract | Bib]


2009 (2)

Now Printing 26, Hideki Isozaki, Tsutomu Hirao, Katsuhito Sudoh, Jun Suzuki, Akinori Fujino, Hajime Tsukada, Masaaki Nagata.
‘A Patient Support System based on Crosslingual IR and Semi-supervised Learning’,
In Proceedings of SIGIR Workshop on Information Access in a Multilingual World, 2009/7.
[Abstract | Bib ]

fig_c25
25, Jun Suzuki, Hideki Isozaki, Xavier, Carreras and Michael Collins.
An Empirical Study of Semi-supervised Structured Conditional Models for Dependency Parsing
In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing (EMNLP-2009), pp. 551–560, 2009/8.
(acceptance rate: 163/475=34%)
[Abstract | Bib]

fig_c24
24, Tsutomu Hirao, Jun Suzuki, and Hideki Isozaki.
A Syntax-Free Approach to Japanese Sentence Compression
In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP (ACL-IJCNLP-2009), pp. 826–833, 2009/8.
(acceptance rate: 121/569=21%)
[Abstract | Bib]


2008 (3)

Now Printing 23, Katsuhito Sudoh, Taro Watanabe, Jun Suzuki, Hajime Tsukada, and Hideki Isozaki.
NTT Statistical Machine Translation System for IWSLT 2008
In Proceedings of International Workshop on Spoken Language Translation (IWSLT-2008), pp. 92–97, 2008/10.
[Abstract | Bib:Link to dblp]

fig_c22.png
22, Jun Suzuki, and Hideki Isozaki.
Semi-Supervised Sequential Labeling and Segmentation using Giga-word Scale Unlabeled Data
In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-08:HLT), pp. 665–673, 2008/6.
(acceptance rate: 119/470=25%)
[Abstract | Bib]

Now Printing 21, Akinori Fujino, Jun Suzuki, and Hideki Isozaki.
Multi-label Text Categorization with Model Combination based on $F_1$-score Maximization
In Proceedings of the 3rd International Joint Conference on Natural Language Processing (IJCNLP-2008), pp. 823–828, 2008/1.
(acceptance rate: 75/270=28%)
[Abstract | Bib:Link to dblp]


2007 (3)

Now Printing 20, Taro Watanabe, Jun Suzuki, Katsuhito Sudoh, Hajime Tsukada, Hideki Isozaki, and Masaaki Nagata.
Larger Feature Set Approach for Machine Translation in IWSLT 2007
In Proceedings of International Workshop on Spoken Language Translation (IWSLT-2007), pp. 111–118, 2007/10.
[Abstract | Bib:Link to dblp]

fig_c19.png
19, Jun Suzuki, Akinori Fujino, and Hideki Isozaki.
Semi-Supervised Structured Output Learning based on a Hybrid Generative and Discriminative Approach
In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL-2007), pp. 764–773, 2007/6.
(acceptance rate: 109/398=27%)
[Abstract | Bib]

Now Printing 18, Taro Watanabe, Jun Suzuki, Hajime Tsukada, and Hideki Isozaki.
Online Large-Margin Training for Statistical Machine Translation
In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL-2007), pp. 764–773, 2007/6.
(acceptance rate: 109/398=27%)
[Abstract | Bib]


2006 (4)

Now Printing 17, Taro Watanabe, Jun Suzuki, and Hajime Tsukada.
NTT Statistical Machine Translation System
The NIST 2006 Machine Translation Evaluation (MT Eval)
[Abstract | Bib]

Now Printing 16, Taro Watanabe, Jun Suzuki, Hajime Tsukada, and Hideki Isozaki.
NTT Statistical Machine Translation for IWSLT 2006
In Proceedings of the International Workshop on Spoken Language Translation (IWSLT-2006), pp. 95–102, 2006/11.
[Abstract | Bib:Link to dblp]

fig_c15.png
15, Jun Suzuki, Erik McDermott, and Hideki Isozaki.
Training Conditional Random Fields with Multivariate Evaluation Measures
In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics Association for Computational Linguistics (COLING/ACL-2006), pp. 217–224, 2006/7.
(acceptance rate: 147/630=23%)
[Abstract | Bib]

Now Printing 14, Norihito Yasuda, Tsutomu Hirao, Jun Suzuki, and Hideki Isozaki.
Identifying Bloggers' Residential Area
In Proceedings of AAAI 2006 spring symposia, 2006.
[Abstract | Bib:Link to dblp]


2005 (4)

Now Printing 13, Hajime Tsukada, and Jun Suzuki.
NTT Site Report
The NIST 2005 Machine Translation Evaluation (MT Eval)
[Abstract |Bib]

Now Printing 12, Hajime Tsukada, Taro Watanabe, Jun Suzuki, Hideto Kazawa, and Hideki Isozaki.
The NTT Statistical Machine Translation System for IWSLT2005
In Proceedings of the International Workshop on Spoken Language Translation (IWSLT-2005), pp. 112–117, 2005/10.
[Abstract | Bib:Link to dblp]

Now Printing 11, Jun Suzuki and Hideki Isozaki.
Sequence and Tree Kernels with Statistical Feature Mining
In Proceedings of the 19th Annual Conference on Neural Information Processing Systems (NIPS-2005), Advances in Neural Information Processing Systems 18, pp. 1321–1328, 2005/12.
(acceptance rate: 207/822=25.2%)
[Abstract | Bib]

fig_c10.png
10, Taku Kudo, Jun Suzuki, and Hideki Isozaki.
Boosting-based Parse Reranking with Subtree Features
In Proceedings of the 43nd Annual Meeting of the Association for Computational Linguistics (ACL-2005), pp. 189–196, 2005/6.
(acceptance rate: 77/423=18%)
[Abstract | Bib]


2004 (3)

Now Printing 9, Tsutomu Hirao, Jun Suzuki, Hideki Isozaki, and Eisaku Maeda.
NTT'S Multiple Document Summarization System for DUC2004
In Proceedings of the 4th Document Understanding Conference (DUC-2004), 2004.
[Abstract | Bib]

Now Printing 8, Tsutomu Hirao, Jun Suzuki, Hideki Isozaki, and Eisaku Maeda.
Dependency-based Sentence Alignment for Multiple Document Summarization
In Proceedings of the 20th International Conference on Computational Linguistics (COLING-2004), 2004/8.
(acceptance rate: N/A)
[Abstract | Bib]

fig_c7.png
7, Jun Suzuki, Hideki Isozaki, and Eisaku Maeda,
Convolution Kernels with Feature Selection for Natural Language Processing Tasks
In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-2004), pp. 119–126, 2004/7.
(acceptance rate: 88/348=25%) 

[Abstract | Bib]


2003 (4)

Now Printing 6, Tsutomu Hirao, Jun Suzuki, Hideki Isozaki, and Eisaku Maeda.
NTT's Multiple Document Summarization System for DUC2003
In Proceedings of the 3rd Document Understanding Conference (DUC-2003), pp. 129–133, 2003.
[Abstract | Bib]

fig_c5.png
5, Jun Suzuki, Yutaka Sasaki, and Eisaku Maeda.
Kernels for Structured Natural Language Data
In Proceedings of the 17th Annual Conference on Neural Information Processing Systems (NIPS-2003), Advances in Neural Information Processing Systems 16, pp. 643–650, 2003/12.
(acceptance rate: 198/717=27.6%)
[Abstract | Bib]

fig_c4.png 4, Jun Suzuki, Hirotoshi Taira, Yutaka Sasaki, and Eisaku Maeda.
Question Classification using HDAG Kernel
In Workshop on Multilingual Summarization and Question Answering (MSQA-2003), pp. 61–68, 2003/7.
[Abstract | Bib]

fig_c3.png
3, Jun Suzuki, Tsutomu Hirao, Yutaka Sasaki, and Eisaku Maeda.
Hierarchical Directed Acyclic Graph Kernel: Methods for Structured Natural Language Data
In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (ACL-2003), pp. 32–39, 2003/7.
(acceptance rate: 71/360=20%)
[Abstract | Bib]


2002 (2)

Now Printing 2, Yutaka Sasaki, Kouji Kokuryou, Hideki Isozaki, Tsutomu Hirao, Jun Suzuki, and Eisaku Maeda.
SAIQA-II: A Trainable Question Answering System
In Demonstrations at Coling 2002.
[Abstract | Bib]

Now Printing 1, Jun Suzuki, Yutaka Sasaki, and Eisaku Maeda.
SVM Answer Selection for Open-Domain Question Answering
In Proceedings of the 19th International Conference on Computational Linguistics (COLING-2002), pp. 974–980, 2002/8.
[Abstract | Bib:Link to dblp]

Technical Reviews

Show Detail

Invided Talks

Show Detail

  • 14, トップカンファレンスへの論文採択に向けて (AI研究分野版)
    人工知能学会合同研究会2019 IJCAI2020に向けた論文書き方セミナー, 2019/11/23
    [ Link | Slide ] (in Japanese)

  • 13, 国際会議への論文の通し方(一般論)
    第4回 統計・機械学習若手シンポジウム / StatsML Symposium'19, 2019/11/15
    [ Link | Slide ] (in Japanese)

  • 12, 単語埋め込みベクトルの利便性向上
    東北大学 情報科学研究科 第76回 情報科学談話, 2019/9/19
    [ Link | Slide ] (in Japanese)

  • 11, トップカンファレンスへの論文採択に向けて(NLP研究分野版) / "Toward paper acceptance at top conferences (NLP research field version)"
    NLP若手の会 (YANS) 第14回シンポジウム / The 14th Symposium of Young Researcher Association for NLP Studies (YANS), 2019/8/26
    [ Link | Slide ] (in Japanese)

  • 10, Usability Enhancements to Neural Word Embeddings
    Third International Workshop on Symbolic-Neural Learning (SNL-2019), 2019/7/11
    [ Link | Slide ]

  • 9, 深層学習による自然言語処理の解釈性/説明性 / Interpretability and explainability of natural language processing with deep learning
    情報処理学会 連続セミナー2019「データ駆動で新時代を切り拓く」第1回:AIと歩む未来(1):自然言語処理の最新動向 / 2019 1st Information Processing Society Seminar “Developing a Data Driven New Era”: The Future with AI (1): The Latest Trends in Natural Language Processing, 2019/6/26
    [ Link(Ja) Link(En) | Slide ] (in Japanese)

  • 8, NAACL 2016 ~会議概要と研究傾向分析~,
    第9回テキストマイニング・シンポジウム 国際会議報告, 2016/09/09
    [ Link | Slide ] (in Japanese)

  • 7, Learning Compact Neural Word Embeddings by Parameter Space Sharing+IJCAI-2016参加レポート,
    河原林ERATO グラフマイニング&WEB&AIセミナー, 2016/07/25
    [ Link | Slide ] (in Japanese)

  • 6, 単語埋め込みベクトル獲得法の現状といくつかの考察,
    産総研人工知能セミナー 第7回AIセミナー 「自然言語処理のAIの最新動向」, 2016/06/21
    [ Link | Slide ] (in Japanese)

  • 5, Supervised Model Learning with Feature Grouping based on a Discrete Constraint
    NII Shonan Meeting, Discrete Algorithms Meet Machine Learning, 2013/08/10-13
    [ Link | Slide ]

  • 4,  大規模教師なしデータからの縮約素性表現学習
    名古屋地区NLPセミナー 第9回, 2011/08/03
    [ Link | Slide ] (in Japanese)

  • 3, Semi-supervised Structured Output Learning using Giga-scale Unlabeled Data
    生命情報工学研究センター セミナー講演, [Link], 2008/
    [ Link | Slide ] (in Japanese)

  • 2, 半教師あり学習による分類法: -現状と自然言語処理への適用-
    言語処理学会第14回年次大会(NLP2008) チュートリアル , 2008/03/17
    [ Link | Slide ] (in Japanese)

  • 1, Semi-supervised Structured Output Learning
     Tokyo Forum on Advanced NLP and TM, 2008/02/12,13
    [ Link | Slide ]


Awards

言語処理学会 論文賞|2015(10) |
言語処理学会 年次大会 | 2006(1) | 2007(2) | 2008(3) | 2010(4) | 2011(5) | 2014(7) | 2014(8) | 2016(12) | 2017(13) | 2018(14) | 2019(17) | 2020(22) | 2020(23) | 2020(24) | 2020(25) | 2020(26) |
人工知能学会 現場イノベーション賞 | 2014(9) |
人工知能学会 研究会 | 2018(16) | SLUD-87(21) |
情報処理学会 研究会 | 2014(6) | 2015(11) | 2019(20) |
NLP若手の会 | 2018(15) | 2019(18) | 2019(19) |

Show Detail


研究費獲得状況


Program comitee member for conferences and journals


Jun Suzuki

Tohoku University
Graduate school of Information Science
System Information Sciences
Intelligent Information Science Communication Science
(Inui-Suzuki Laboratory)

NTT Communication Science Laboratories
Innovative Communication Laboratory
Linguistic Intelligence Research Group

E-mail: jun [dot] suzuki [at] ecei [dot] tohoku [dot] ac [dot] jp