Yuki Arase

Professor (Japanese page)

School of Computing, Tokyo Institute of Technology, Japan

Arase Lab

Email: arase@ (add the domain: c.titech.ac.jp)

Twitter: @Yuki_arase

I am a professor at the School of Computing, Tokyo Institute of Technology, Japan. After obtaining my PhD in Information Science from Osaka University (2010), I worked for Microsoft Research Asia, where I started NLP research that continues to captivate me to this day. My research interests focus on paraphrasing and NLP technology for language education and healthcare.

I’m recruiting PhD students and postdocs. Please send me your CV with a publication list if you are interested. Note that we do not have “research student” positions.

---

Publications / CV / ACL Anthology / Google Scholar / Semantic Scholar

---

News

• Our paper has been accepted by EMNLP2024 Findings: T. Zetsu, Y. Arase, and T. Kajiwara. Edit-Constrained Decoding for Sentence Simplification, in Proc. of EMNLP 2024 Findings (Nov. 2024 to appear).
• Arase Lab website got launched!
• Joined Tokyo Institute of Technology

(Last update: 2024/09/20)

Research

For more details, please see Research page.

Paraphrase generation & recognition

Paraphrasing takes various forms of monolingual text transformations, such as text simplification, rewriting, and style transfer. We work on both recognition and generation. The core technologies are intelligent phrase alignment and controllable paraphrase generation.

Related papers: DIRECT, phrase alignment, Round-trip translation for paraphrasing, SAPPHIRE

Representation learning

Vector representation of words, phrases, and sentences are the very basis for NLP research. We study

1. sophisticated representations for word meaning in context and multilingual sentences,
2. efficient pre-trained models for words and phrases, and
3. representations for few-shot learning.

Related papers: WiC representation, disentangling sentence meaning, transfer fine-tuning, label representation for few-shot learning, tiny word embedding

NLP for language education & learning

As a central application of our research outcomes, we develop technologies for language learning and education supports. Our technology covers from fine-grained lexical-level transformations to coarse-grained text-level processing.

Related papers: definition generation, controllable text simplification, CEFR-based lexical simplification, fill-in-the-blank quiz generation

Selected Recent Publications

• Y. Ogasa, T. Kajiwara, Y. Arase. Controllable Paraphrase Generation for Semantic and Lexical Similarities, in Proc. of Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 3927–3942 (May 2024).
• R. Miyano, T. Kajiwara, Y. Arase. Self-Ensemble of N-best Generation Hypotheses by Lexically Constrained Decoding, in Proc. of Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), pp. 14653-14661 (Dec. 2023).
• Y. Arase, H. Bao, and S. Yokoi. Unbalanced Optimal Transport for Unbalanced Word Alignment, in Proc. of the Annual Meeting of the Association for Computational Linguistics (ACL 2023), pp. 3966–3986 (July 2023).
• Y. Arase, S. Uchida, and T. Kajiwara. CEFR-based Sentence Difficulty Annotation and Assessment, in Proc. of Conference on Empirical Methods in Natural Language Processing (EMNLP2022), pp. 6206-6219 (Dec. 2022).
• Y. Kuroda, T. Kajiwara, Y. Arase, and T. Ninomiya. Adversarial Training on Disentangling Meaning and Language Representations for Unsupervised Quality Estimation, in Proc. of International Conference on Computational Linguistics (COLING 2022), pp. 5240-5245 (Oct. 2022).
• H. Huang, T. Kajiwara, and Y. Arase. Definition Modelling for Appropriate Specificity, in Proc. of Conference on Empirical Methods in Natural Language Processing (EMNLP2021), pp. 2499–2509 (Nov. 2021).
• N. Tiyajamorn, T. Kajiwara, Y. Arase, and M. Onizuka. Language-agnostic Representation from Multilingual Sentence Encoders for Cross-lingual Similarity Estimation, in Proc. of Conference on Empirical Methods in Natural Language Processing (EMNLP2021), pp. 7764–7774 (Nov. 2021).
• Y. Arase and T. Kajiwara. Distilling Word Meaning in Context from Pre-trained Language Model, in Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 534–546 (Nov. 2021). code
• J. Takayama, T. Kajiwara, and Y. Arase. DIRECT: Direct and Indirect Responses in Conversational Text Corpus, in Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 1980–1989 (Nov. 2021). data
• S. Ohashi, J. Takayama, T. Kajiwara, and Y. Arase. Distinct Label Representations for Few-Shot Text Classification, in Proc. of the Annual Meeting of the Association for Computational Linguistics and International Joint Conference on Natural Language Processing (ACL-IJCNLP2021), pp. 831-836 (Aug. 2021).
• Y. Arase and J. Tsujii: Transfer Fine-Tuning of BERT with Phrasal Paraphrases, in Computer Speech & Language, Vol. 66 (Mar. 2021). paper 
• S. Ohashi, M. Isogawa, T. Kajiwara and Y. Arase: Tiny Word Embeddings Using Globally Informed Reconstruction, in Proc. of International Conference on Computational Linguistics (COLING2020), pp. 1199–1203 (Dec. 2020).
• Y. Arase and J. Tsujii: Compositional Phrase Alignment and Beyond, in Proc. of Conference on Empirical Methods in Natural Language Processing (EMNLP2020), pp. 1611–1623 (Nov. 2020).
• J. Takayama and Y. Arase: Consistent Response Generation with Controlled Specificity. in Proc. of Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 4418–4427 (Nov. 2020).
• S. Ohashi, J. Takayama, T. Kajiwara, C. Chu, Y. Arase. Text Classification with Negative Supervision, in Proc. of Annual Meeting of the Association for Computational Linguistics (ACL 2020), pp. 351–357 (July 2020).
• T. Kajiwara, B. Miura, and Y. Arase. Monolingual Transfer Learning via Bilingual Translators for Style-Sensitive Paraphrase Generation, in Proc. of the AAAI Conference on Artificial Intelligence (AAAI 2020), pp. 8042-8049, (Feb. 2020).
• Y. Arase and J. Tsujii: Transfer Fine-Tuning: A BERT Case Study, Proc. of Conference on Empirical Methods in Natural Language Processing (EMNLP2019), pp. 5396–5407 (Nov. 2019).
• J. Takayama, E. Nomoto, and Y. Arase: Dialogue Breakdown Detection Robust to Variations in Annotators and Dialogue Systems, Computer Speech & Language, Vol. 54, pp. 31-43 (Mar. 2019).
• Y. Arase and J. Tsujii: SPADE: Evaluation Dataset for Monolingual Phrase Alignment, in Proc. of Language Resources and Evaluation Conference (LREC 2018), (May 2018).

Academic Service

• PC Chair: IJCNLP-AACL2023, SNL2021
• Senior Area Chair: ACL2023
• Area Chair: ARR, ACL2020, 2021, EMNLP2021, COLING 2024
• Publicity and Social Media Chair: ACL2024
• Publication Chair for ACL2020
• Reviewer: ACL, EMNLP, NAACL, EACL, TACL, Computational Linguistics, etc.
• Member-at-large: Asian Federation of Natural Language Processing(AFNLP)
• Director: The Association for Natural Language Processing, Japan, Information Processing Society of Japan