Tohoku EduNLP Lab

Tohoku EduNLP Lab is a team at Tohoku University, working on computational approaches for human language, aiming to apply the cutting-edge AI technologies to humanities including education as well as society.

東北大学教育言語処理研究室は人間の言葉に計算機科学的にアプローチする研究を行っているチームです。 言語の計算科学を教育学を含めた人文科学に適用し、社会に役立てることを目指しています。

Contact Info

27-1 Kawauchi, Aoba-ku,
Sendai, Miyagi, JAPAN 9808576
〒980-8576
宮城県仙台市青葉区川内27-1
東北大学 川内南キャンパス
文科系総合研究棟

News Category:

paper

funayama-aied2022
Read More

Paper Accepted for AIED 2022

The following paper with Funayama-san in Inui lab has been accepted for AIED 2022!

Hiroaki Funayama, Tasuku Sato, Yuichiroh Matsubayashi, Tomoya Mizumoto, Jun Suzuki and Kentaro Inui. Balancing Cost and Quality: An Exploration of Human-in-the-loop Frameworks for Automated Short Answer Scoring, The 23rd International Conference on Artificial Intelligence in Education (AIED2022), pp.xxx-xxx, July 2022.

konno-emnlp2021
Read More

Paper Accepted for EMNLP 2021

The following paper with Konno-san has been accepted for EMNLP 2021 main conference!

Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution
Ryuto Konno, Shun Kiyono, Yuichiroh Matsubayashi, Hiroki Ouchi and Kentaro Inui

paper DOI: https://arxiv.org/abs/2104.07425

kikuchi-nlp2021
Read More

Presentations at NLP 2021

We made the following three presentations at NLP 2021.

  • D4-3 項目採点技術に基づいた和文英訳答案の自動採点 ○菊地正弥, 尾中大介, 舟山弘晃, 松林優一郎, 乾健太郎 (東北大/理研)
  • C9-4 事前学習とfinetuningの類似性に基づくゼロ照応解析 ○今野颯人 (東北大), 清野舜 (理研/東北大), 松林優一郎 (東北大/理研), 大内啓樹 (理研), 乾健太郎 (東北大/理研)
  • WS3-6 実用的な自動採点のための確信度推定と根拠事例の提供 ○舟山弘晃(東北大/理研),王天奇(東北大/理研),松林優一郎(東北大/理研),水本智也(フューチャー/理研),佐藤汰亮(東北大/理研),鈴木潤(東北大/理研),乾健太郎(東北大/理研)

konno-accepted-coling2020
Read More

Paper Accepted for COLING 2020

The following paper with Konno-san has been accepted for COLING 2020!

An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution.
Ryuto Konno, Yuichiroh Matsubayashi, Shun Kiyono, Hiroki Ouchi, Ryo Takahashi and Kentaro Inui.
In Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020) pp.4956–4968, December 2020.

Read More

Paper Accepted for Journal of Natural Language Processing

The following paper with Abe-san in Inui lab has been accepted for Journal of Natural Language Processing.

Kaori Abe, Yuichiroh Matsubayashi, Naoaki Okazaki and Kentaro Inui.
Multi-dialect Neural Machine Translation for 48 Low-resource Japanese Dialects.
Journal of Natural Language Processing. Volume 27, Number 4, pp.781-800, December 2020.

Paper DOI: https://doi.org/10.5715/jnlp.27.781

funayama-ACLSRW2020
Read More

Paper accepted at ACL SRW 2020

The following paper with Funayama-san in Inui lab has been accepted for ACL SRW 2020!

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 SRW), pp. 237–243, July 2020.

Paper

Presentation Video

Read More

Paper Accepted for BUCLD44

The paper "The Input to Verb Learning in Japanese: Picture Books for Syntactic Bootstrapping" has been accepted for BUCLD 44.

Naho Orita, Asumi Suzuki, Yuichiro Matsubayashi.
The Input to Verb Learning in Japanese: Picture Books for Syntactic Bootstrapping.
In BUCLD 44: Proceedings of the 44th annual Boston University Conference on Language Development (BUCLD) edited by Megan M. Brown and Alexandra Kohut, pp. 457-464.