PhD student in Computer Science and Engineering @notredame. Ex-intern @SakanaAILabs, @megagonlabs. formerly @EdinburghUni, @naist_nlp. #linguistics #NLProc
Joined June 2022
- Tweets59
- Following87
- Followers135
- Likes70
I will be presenting two papers at EMNLP 2025 in Suzhou 🇨🇳!
If you are interested in low-resource NLP, speech recognition, machine translation, retrieval-augmented generation, feel free to contact me for a quick chat!
I will be also on the job market next year.
📕 “Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive‑k”
Oral presentation @ Question Answering
11/5 Wed. 15:15
📄arxiv: arxiv.org/abs/2506.08479
⚙️code: github.com/megagonlabs/adapt…
📗 “Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark”
@ Poster session 6
11/7 Fri. 10:30
📄arxiv: arxiv.org/abs/2508.20511
⚙️code: github.com/ctaguchi/LSLB
Chihiro Taguchi@EMNLP2025 retweeted
Our paper is accepted to the main conference of EMNLP 2025🎉
This is my first paper as the primary mentor of an intern! I’d like to send huge kudos to @taguchi_c for the amazing work and dedication👏
arxiv.org/abs/2506.08479
Happy to share that two of my first-author papers have been accepted at #EMNLP2025 Main! (1/4)
📃Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark arxiv.org/abs/2508.20511
This paper reports the systematic issues in FLORES+, the multilingual MT benchmark, in its translation quality and the source sentence selection. (3/4)
I plan to attend the conference in person, so drop me a DM if you will be in Suzhou!
#RAG #LLM #machinetranslation #lowresourcelanguages #multilingual #NLP #linguistics
(4/4)
I completed my 3-month internship at @MegagonLabs last week. Massive thanks to @SAYg_7 and @nikita_bhutani I learned so much, and it was a very productive learning experience. I hope to see the team members again soon! (also hopefully the paper is coming out soon 🚀)
Chihiro Taguchi@EMNLP2025 retweeted
Midwest Speech and Language Days will be held Apr 15-16 at @NotreDame! Abstract submissions are due Mar 20, and registration deadline is Mar 27. Financial assistance for students (lodging, poster printing) is available. nlp.nd.edu/msld25
Chihiro Taguchi@EMNLP2025 retweeted
Megagon Labs has welcomed @taguchi_c, PhD student at the @NotreDame, to our office for his winter internship. 🎉 He is conducting research on Retrieval-augmented generation (#RAG) and long-context language models (#LCLMs), mentored by @SAYg_7 and @Nikita_Bhutani #AI #LLMs #NLProc
Chihiro Taguchi@EMNLP2025 retweeted
Web ツールも公開しています： softmatcha.github.io/
ノートルダムの田口さんに参加いただいたことにより、英語・日本語に次いで、ラテン語（？！）でも検索できるようになりました。西洋古典にご興味のあるみなさん、ぜひ遊んでみてください。
📑はこちら： openreview.net/forum?id=Q6PA…
Chihiro Taguchi@EMNLP2025 retweeted
バカでかコーパスを超高速に検索できる柔らかい grep/KWIC を作る話が #ICLR2025 に採択されました。
NLP + 理論計算機科学 + 言語学 のプレイヤーの合作です。
異なる分野のプロが集まる魅力をひしひし感じましたし、信じられないスピード感での議論・アルゴリズム改善・論文生成が超愉しかったです。
Chihiro Taguchi@EMNLP2025 retweeted
Our paper has been accepted at #ICLR2025🎉
SoftMatcha finds query patterns that match not only exactly, e.g., grep, but also semantically similar ones levearaging word embeddings.
Moreover, our soft yet efficient matcher can search billion-word corpora in 0.1 sec on CPUs🚀
Chihiro Taguchi@EMNLP2025 retweeted
Congratulations to @taguchi_c for winning a @lucy_institute Societal Impact Award for his work on creating language technologies for the Kichwa language community in Ecuador! @ND_CSE
youtube.com/watch?v=HjsNOEd7…
Chihiro Taguchi@EMNLP2025 retweeted
🚀次回のNLPコロキウムのお知らせ
講演者：田口智大 @taguchi_c (@notredame)
日時：9/11 (水) 12:00- JST
人間👶にとって学びづらい言語は音声認識モデル🤖にとっても学びづらいのでしょうか。文字体系と音韻に着目した調査結果のご紹介です。[ACL'24 Outstanding Paper]
nlp-colloquium-jp.github.io/…
Chihiro Taguchi@EMNLP2025 retweeted
The paper studies the impact of various linguistic factors on automatic speech recognition accuracy. Orthographic complexity makes ASR more difficult, while phonological complexity doesn't. arxiv.org/abs/2406.09202
Chihiro Taguchi@EMNLP2025 retweeted
Congratulations to Chihiro Taguchi @taguchi_c for winning an SAC/Outstanding Paper Award at #ACL2024 for his paper, "Language complexity and speech recognition accuracy: orthographic complexity hurts, phonological complexity doesn't"!
I was awarded an Outstanding Paper Award and an Area Chair’s Award at #ACL2024!
I’m thrilled to win them for the research question I proposed myself and worked on with my supervisor @davidweichiang.
Missed my poster? Don’t worry! I’ll be giving an oral presentation in the session “Speech recognition, text-to-speech and spoken language understanding” in World Ballroom C from 10:30am! (my talk will start at 11am).
Today at ACL 2024 I’ll present my poster “Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn't” at Poster Session D from 10:30am!
Please stop by :)
ArXiv: arxiv.org/abs/2406.09202