Sign in

Seth Aycock

@sethjsa.bsky.social
57 followers 111 following 2 posts

PhD student in NLP, focusing on low-resource translation with LLMs. University of Amsterdam

PostsRepliesMedia
Reposted by Seth Aycock
Patricia Schmidtova @patuchen.bsky.social · 17/06/2026
Dates: Sample data: already available on our website! www2.statmt.org/wmt26/multil... Test data release: July 1st, 2026 Submission deadline: August 1st, 2026 If you are interested in joining, please fill out our Expression of Interest form here: forms.gle/bMbL2SPPWNi9... See you in Budapest!
www2.statmt.org
Multilingual Instruction Shared Task
021
Reposted by Seth Aycock
Vilém Zouhar @zouhar.bsky.social · 16/06/2026
We are at @eamt2026.bsky.social with a large-scale stealth project called "[redacted] Translation [redacted]". Looking for contributors across all languages to challenge MTs. Talk to @patuchen.bsky.social, @sethjsa.bsky.social and me to be a coauthor!
4123
Reposted by Seth Aycock
Institute of Formal and Applied Linguistics @ufal.mff.cuni.cz · 26/03/2026
How Important is ‘Perfect’ English for Machine Translation Prompts? by @patuchen.bsky.social, @niyatibafna.bsky.social, @sethjsa.bsky.social , @gianlucavico.bsky.social ,W. Kamzela, @kathaem.bsky.social & @zouharvi.bsky.social aclanthology.org/2026.finding... TL;DR: Prompt errors < prompt choice
1162
Seth Aycock @sethjsa.bsky.social · 09/09/2025
MT Marathon this year organised by @helsinki-nlp.bsky.social was a great week - I presented my research on chain-of-thought for machine translation, worked on a mini-research project, and explored the wonderful city of Helsinki including a few trips to the sauna 🫠
040
Reposted by Seth Aycock
Raphaël Merx @rapha.dev · 08/05/2025
My favourite ICLR paper so far. Methodology, findings and their implications are all very cool. In particular Fig. 2 + this discussion point:
041
Seth Aycock @sethjsa.bsky.social · 25/04/2025
Pleased to announce our paper was accepted at ICLR 2025 as a Spotlight! I will present our poster on Saturday April 26, 3-5pm, Poster #241. Hope to see you there! arxiv.org/abs/2409.19151
arxiv.org
Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?
Extremely low-resource (XLR) languages lack substantial corpora for training NLP models, motivating the use of all available resources such as dictionaries and grammar books. Machine Translation from ...
0173