iiinova — where your digital self keeps evolving

Atsuki Yamaguchi @gucciiiii.bsky.social · 25/01/2025

The ARR reviewer guidelines have undergone revisions, and they have become so clear now regarding what to do and what not to do in reviewing. (2/2) aclrollingreview.org/reviewerguid...

000

Atsuki Yamaguchi @gucciiiii.bsky.social · 25/01/2025

I think all ARR reviewers should go through the common review issues section before reviewing, regardless of their reviewing experience. I've received too many "The authors could also do [extra experiment X]" comments as weaknesses in this cycle. This is really annoying. (1/2)

aclrollingreview.org

ARR Reviewer Guidelines

A peer review platform for the Association for Computational Linguistics

100

Reposted by Atsuki Yamaguchi

Anna Rogers @annarogers.bsky.social · 15/01/2025

In #nlp org news @aclmeeting.bsky.social: there were a few clarifications to ACLPUB, based on frequent issues on ARR. TLDR: - don't abuse font sizes for figures and tables - limitations & ethical considerations sections go after conclusion, no page breaks - two-column formatting for appendices

5155

Reposted by Atsuki Yamaguchi

Anthony Hughes @antjhughes.bsky.social · 22/12/2024

Wrote up my first piece of PhD work last week! 🧵 Summarization via LMs is great at extracting info from documents, but how does summarization look in sensitive settings where privacy-preservation is essential? Short answer: LMs are poor privacy preservers. Arxiv: arxiv.org/abs/2412.12040

arxiv.org

How Private are Language Models in Abstractive Summarization?

Language models (LMs) have shown outstanding performance in text summarization including sensitive domains such as medicine and law. In these settings, it is important that personally identifying info...

173

Reposted by Atsuki Yamaguchi

SheffieldNLP @sheffieldnlp.bsky.social · 06/12/2024

🎉 Exciting news from SheffieldNLP! Check out our recent publications featured at COLING 2025 and in Systematic Reviews journal! 📚✨

141