Postdoctoral researcher Paul Reisert presented on the following topic at theInformal Workshop on Argumentation/Argument Mining .

Informal Workshop on Argumentation/Argument Miningにて、Paul Reisert（特別研究員）が下記の発表を行いました。

• Paul Reisert.
  “Towards Improving Current Automatic Essay Scoring and Constructive Feedback Systems”.

The following paper by 3rd year Ph.D. candidate Qin Dai has been presented at the Third International Workshop on SCIentific DOCument Analysis(SCIDOCA2018).

2018年11月12日から13日にかけて開催されたThird International Workshop on SCIentific DOCument Analysis(SCIDOCA2018)にて、代勤（博士3年）が下記の発表を行いました。

• Qin Dai, Naoya Inoue, Paul Reisert and Kentaro Inui.
  “Scientific Knowledge Acquisition via the Interaction between Relation Extraction and Knowledge Graph Completion”.

Our team placed 27th out of 40 at the annual Ekiden relay race, followed by an Oden party.

恒例の駅伝大会が開催され40チーム中27位という結果でした。駅伝後には、おでんパーティーも行いました。

Dr. Satoshi Hara from the Osaka University Institute of Industrial Science gave a lecture titled “Explaining the rationale behind ML model selection”. (MiCS).

大阪大学産業科学研究所の原聡氏にお越しいただき、「機械学習モデルの判断根拠の説明」という表題でご講演いただきました。（みちのく情報伝達学セミナー）

The research from Prof. Kentaro Inui’s team on AI scoring and correcting Japanese essay writing has been published on the November 8th edition of the Nikkei newspaper (Japanese), titled as [STEP Eiken, AI scoring “speaking” and “writing” with partial points as well].

乾健太郎教授が開発に関わっている国語の記述問題を採点・添削するAIに関する研究が、11月8日（木）の日本経済新聞【英検、AIが採点　「話す」と「書く」で部分点も】に掲載されました。

A message from the Lab to students considering joining the Tohoku University Inui-Suzuki Laboratory: http://www.cl.ecei.tohoku.ac.jp/index.php?Message%20to%20Students (Japanese only).

東北大学 乾・鈴木研究室への配属を検討している皆さんに向けて、研究室一同からのメッセージを掲載しました

http://www.cl.ecei.tohoku.ac.jp/index.php?Message%20to%20Students

Time：

• 11/9(Fri) 18:00-
• 11/12(Mon) 18:00-
• 11/13(Tue) 18:00-
• 11/14(Wed) 18:00-
• 11/15(Thu) 18:00-

Location：

Research Building No.1-Electrical Engineering and Applied Physics, Room 661

Topics：

• Introduction of the lab’s research topics and research environments by Professor Inui, Associate Professor Suzuki, and Assistant Professor Inoue
• Q&A session with the lab’s students

Appointments are not required and anyone can join the meeting at any time. If none of the above time slots suits you, please visit the page Visit the Laboratory to make an appointment for yourself.

日時

• 11月9日(金) 18:00-
• 11月12日(月) 18:00-
• 11月13日(火) 18:00-
• 11月14日(水) 18:00-
• 11月15日(木) 18:00-

場所：

電気系1号館6階661

内容

• 乾教授、鈴木准教授、井之上助教が研究内容や研究室環境を紹介します
• 研究室の学生が皆さんからの質問にお答えします

アポは不要、途中の入退室も構いません。お気軽にお越しください。また、その他の時間帯もいつでも見学会で対応します。こちらからお問い合わせください。

The following papers have been accepted tothe Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19) (Acceptance rate 16.2 % = 1,150 / 7,095).

The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19)に下記の論文が採択されました（採択率 16.2 % = 1,150 / 7,095）。

• Shun Kiyono, Jun Suzuki, Kentaro Inui.
  “Mixture of Expert/Imitator Network: Scalable Semi-supervised Learning Framework”.
• Sho Takase, Jun Suzuki, Masaaki Nagata.
  “Character n-gram Embeddings to Improve RNN Language Models”.

The following papers are presented at the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018)and co-located workshops.

10月31日からベルギーで開催されたThe 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018) および併催WSで下記の発表を行いました。

Main Conference

• Sho Yokoi, Sosuke Kobayashi, Kenji Fukumizu, Jun Suzuki, and Kentaro Inui.
  “Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions”.
• Hiroki Ouchi, Hiroyuki Shindo, and Yuji Matsumoto.
  “A Span Selection Model for Semantic Role Labeling”.
• Saku Sugawara, Kentaro Inui, Satoshi Sekine, and Akiko Aizawa.
  “What Makes Reading Comprehension Questions Easier?”.
• Sho Takase, Jun Suzuki, and Masaaki Nagata.
  “Direct Output Connection for a High-Rank Language Model”.

Workshops

The 4th Workshop on Noisy User-generated Text (W-NUT)

• Ryo Nagata, Tomoya Mizumoto, Yuta Kikuchi, Yoshifumi Kawasaki and Kotaro Funakoshi.
  “A POS Tagging Model Designed for Learner English”.

The 5th Workshop on Argument Mining (Argmining 2018)

• Paul Reisert, Naoya Inoue, Tatsuki Kuribayashi and Kentaro Inui.
  “Feasible Annotation Scheme for Capturing Policy Argument Reasoning using Argument Templates”.

The Ninth International Workshop on Health Text Mining and Information Analysis (LOUHI 2018)

• Diana Galvan, Naoaki Okazaki, Koji Matsuda and Kentaro Inui.
  “Investigating the Challenges of Temporal Relation Extraction from Clinical Text”.

Analyzing and interpreting neural networks for NLP (BlackboxNLP)

• Shun Kiyono, Sho Takase, Jun Suzuki, Naoaki Okazaki, Kentaro Inui and Masaaki Nagata.
  “Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder models”.

The staff members held a celebration for the new dads who each welcomed a beautiful child this month: postdoctoral researcher Hiroki Ōuchi and visiting researcher Shōichi Naitō. Please build a bright and fun, wonderful home!

先月お子様が誕生した、大内啓樹（特別研究員）と内藤昭一（客員研究員）にスタッフ一同から出産祝いをお贈りしました。明るく楽しい、素敵なご家庭を築いてくださいね！

The lecture Professor Kentarō Inui gave at the Asahi Earth Conference 2018 has been published in the digital edition of the Asahi newspaper (Japanese only) under the title “Asahi Conference 2018: Dialogue with things, prosperous living”

乾健太郎教授が講演をおこなった朝日地球会議2018の様子が、10月18日（木）の 朝日新聞及び朝日新聞デジタル【モノとも対話、暮らし豊かに　朝日地球会議２０１８】に掲載されました。

The following paper has been accepted to Third International Workshop on SCIentific DOCument Analysis（SCIDOCA2018）.

Third International Workshop on SCIentific DOCument Analysis（SCIDOCA2018）に下記の論文が採択されました。

• Qin Dai, Naoya Inoue, Paul Reisert and Kentaro Inui.
  “Scientific Knowledge Acquisition via the Interaction between Relation Extraction and Knowledge Graph Completion”.

RIKEN’s Dr. Hitomi Yanaka visited our laboratory and gave a talk titled “Towards understanding textual entailment and similarity”.(MiCS).

理化学研究所の谷中瞳氏にお越しいただき、「Towards understanding textual entailment and similarity.」という表題でご講演いただきました。（みちのく情報伝達学セミナー）

Inui Laboratory’s previous member who is currently affiliated with AIST visited the laboratory and gave a talk titled “The future of lyrics processing”. Definitely come back soon!

乾研究室OBで産業技術総合研究所の渡邉研斗氏にお越しいただき、「歌詞情報処理が切り拓く未来」についてショートトークをしていただきました。どうぞ、また来てくださいね！

Congratulations to Reina Akama (M2) for receiving their Master’s degree! We hope for your continued success in the future.

赤間 怜奈さん（修士2年）、ご修了おめでとうございます！これからの益々のご活躍をお祈り申し上げます。

Members of our laboratory recently enjoyed a nice stew and barbeque near the Hirose River. Family members and new laboratory members both joined, and the party was very festive!

広瀬川のせせらぎの下、芋煮とバーベキューを堪能しました。新メンバーや研究室メンバーのご家族も加わり、とても賑やかな会になりました。

A laboratory excursion was held for the first time in a while. Members visited both Minami-Sanriku shopping center and Tatsuganesan and had fun at the hot spring and banquet.

2018年9月11日から12日にかけて久しぶりの研究室旅行が開催されました。南三陸さんさん商店街、田束山を訪れ、温泉や宴会も楽しみました。

An interview with Professor Kentarō Inui was featured in the Recruit Advanced Research Institute6th Signpost of Learning.

乾健太郎教授のインタビュー記事がリクルート進学総研 第6回 学びのみちしるべ【知能情報学】に掲載されました。

The following papers have been accepted to the 32nd Pacific Asia Conference on Language, Information and Computing (PACLIC 32).

the 32nd Pacific Asia Conference on Language, Information and Computing (PACLIC 32)に下記の論文が採択されました。

• Qin Dai, Naoya Inoue, Paul Reisert and Kentaro Inui.
  “Improving Scientific Relation Classification with Task Specific Supersense”.
• Shun Kiyono, Sho Takase, Jun Suzuki, Naoaki Okazaki, Kentaro Inui and Masaaki Nagata.
  “Reducing Odd Generation from Neural Headline Generation”.
• Kaori Abe, Yuichiroh Matsubayashi, Naoaki Okazaki and Kentaro Inui.
  “Multi-dialect Neural Machine Translation and Dialectometry”.
• Tsubasa Tagami, Hiroki Ouchi, Hiroki Asano, Kazuaki Hanawa, Kaori Uchiyama, Kaito Suzuki, Kentaro Inui, Atsushi Komiya, Atsuo Fujimura, Ryo Yamashita, Hitofumi Yanai and Akinori Machino.
  “Suspicious News Detection Using Micro Blog Text”.

Second-year Master students Shōta Sasaki and Hono Shirai received awards at the 13th Symposium of YANS (Japanese only) for their presentations.

• Shōta Sasaki, Jun Suzuki, Kentarō Inui
  “Reconstruction of word vectors based on subwords”
• Hono Shirai, Naoya Inoue, Kentarō Inui
  “Toward mining pros and cons of information science papers”

2018年8月27日から29日にかけて行われた、NLP若手の会（YANS）第13回シンポジウムにて下記発表を行い、佐々木翔大（修士2年）と白井穂乃（修士2年）が奨励賞を受賞しました。

• 佐々木翔大, 鈴木潤, 乾健太郎．
  “サブワードに基づく単語ベクトルの再構築”．
• 白井穂乃, 井之上直也, 乾健太郎．
  “情報科学論文からの技術の利点・欠点のマイニングに向けて”．

Assistant professor Naoya Inoue’s team has received the Hackathon award.

また、開催されたハッカソンにて、井之上直也助教が参加したチームがハッカソン賞を受賞しました.