We will present a paper at NAACL 2022 (2022/7) †

• Zhuoyuan Mao, Chenhui Chu, Raj Dabre, Haiyue Song, Zhen Wan, Sadao Kurohashi:
  When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation? (Findings)

We will present a paper at ACL 2022 Student Research Workshop (2022/5) †

• Yongmin Kim, Chenhui Chu, Sadao Kurohashi:
  Flexible Visual Grounding

Associate Professor Chu received a Google Research Scholar Award for his Visual Scene-Aware Machine Translation research proposal. (2022/4) †

We will present the following papers at LREC2022 (2022/6) †

• Fei Cheng, Shuntaro Yada, Ribeka Tanaka, Eiji ARAMAKI and Sadao Kurohashi:
  JaMIE: A Pipeline Japanese Medical Information Extraction System with Novel Relation Annotation

• Felix Giovanni Virgo, Fei Cheng, Sadao Kurohashi:
  Improving Event Duration Question Answering by Leveraging Existing Temporal Information Extraction Data

• Taro Okahisa, Ribeka Tanaka, Takashi Kodama, Yin Jou Huang and Sadao Kurohashi:
  Constructing a Culinary Interview Dialogue Corpus with Video Conferencing Tool

• Yihang Li, Shuichiro Shimizu, Weiqi Gu, Chenhui Chu and Sadao Kurohashi:
  VISA: An Ambiguous Subtitles Dataset for Visual Scene-aware Machine Translation

The following paper received the Special Committee Award of the 28-th annual meeting of the association for natural language processing (2022/3) †

• Rikito Takahashi, Chenhui Chu and Sadao Kurohashi:
  Abstractive Captioning from Multiple Videos
• Yihang Li, Shuichirou Shimizu, Chenhui Chu and Sadao Kurohashi:
  Towards the Construction of Multimodal Machine Translation Dataset Focusing on Ambiguity of Translation

We have released the app for Japanese composition study "Let's get started with Ichimaru! Kotobamusubi" developed in the research project with the Japan Kanji Aptitude Testing Foundation. †

The following article by Takumi Yoshikoshi and Hirokazu Kiyomaru received the WHI award of Qiita Advent Calendar. †

• Development of an automatic Japanese wordplay generator (in Japanese)

The following paper was accepted to AAAI 2022 †

• Hirokazu Kiyomaru and Sadao Kurohashi:
  Minimally-Supervised Joint Learning of Event Volitionality and Subject Animacy Classification

Search Engine Infrastructure based on Deep Natural Language Processing †

The essential purpose of information retrieval is not to retrieve just a relevant document but to acquire the information or knowledge in the document. We have been developing a next-generation infrastructure of information retrieval on the basis of the following techniques of deep natural language processing: precise processing based not on words but on predicate-argument structures, identifying the variety of linguistic expressions and providing a bird's-eye view of search results via clustering and interaction.

Machine Translation †

To bring automatic translation by computers to the level of human translation, we have been studying next-generation methodology of machine translation on the basis of text understanding and a large collection of translation examples. We have already accomplished practical translation on the domain of travel conversation, and constructed a translation-aid system that can be used by experts of patent translation.