NLP researcher working on paraphrasing, NLP for language education, machine translation, and dialogue systems. MSRA ⏩ Osaka University ⏩ Professor
@TITECH
I’m so thrilled about this opportunity! Thank you for all of your warm support🙏✨ I'll be serving as a conference officer. Will work hard to support the ACL conferences’ healthy growth.
Looking forward to working with you
@barbara_plank
and the whole Exec team!
I'm excited to share that I was elected VP-elect for the ACL (Association for Computational Linguistics) - This is a great honor and I expect also a challenge. I will try to do my best in the years to come. Looking fwd to join the board w/
@Yuki_arase
Good news during summer holiday :)
Y. Arase and J. Tsujii: Injecting Phrasal Paraphrase Relation into Sentence Representation for Semantic Equivalence Assessment (the title is subject to change)
will be presented at
#emnlp2019
Introducing OTAlign, optimal transport (OT) based monolingual word alignment.
We established a connection between the family of OT and monolingual word alignment concerning the null alignment ratio. (1/3)
📄 w/
@levelfour_
and
@sho_yokoi_
#ACL2023NLP
Monolingual alignment, anyone?
Our
#ACL2023NLP
paper "Unbalanced Optimal Transport for Unbalanced Word Alignment" w/
@levelfour_
and
@sho_yokoi
shows the family of optimal transport are natural and powerful tools for this problem.
More information coming soon.
#NLProc
学生さんが主著の論文が採択されました。11/10まで無料でアクセスできるようです。
J. Takayama, E. Nomoto, and Y. Arase: Dialogue Breakdown Detection Robust to Variations in Annotators and Dialogue Systems, in Computer Speech and Language
Our paper, CEFR-based Sentence Difficulty Annotation and Assessment (w/ S. Uchida and
@moguranosenshi
), will show up in
#EMNLP2022
. We'll release 17k sentences annotated with CEFR levels assigned by English-education professionals on time for the conference. Stay tuned :)
Our paper (w/ S. Kadotani) for parse forest mapping got accepted at
#starsem2023
, co-located with
#acl2023
.
This completes (for now) our series of papers on syntactic phrase alignment 🥳()
Happy for that!
#NLProc
Safely landed on Singapore for
#EMNLP2023
🇸🇬 Our poster on N-best hypotheses ensembling will be on the first day afternoon! Interested in re-ranking for decoding? Please come to talk with us!
Our human eval indicated GPT-4 did advance simplification quality yet still struggles to do sensible lexical/phrasal paraphrasing. Also metrics sensitive enough for such advanced simplification are coveted. Work done by our student
@gosenkin
#NLProc