#HumanLevelTranslation #neuralempty in the middle of nowhere

At the current translation quality level, we will need +5 BLEU to get significant results. #neuralempty

Findings from #WMT23.Our Chat4 friend is in the winning group across tasks.Most submissions still use from scratch training.Less constrained (low resource) submissions than before.More test suit submissions!.Low resource results TBD (tech issue).#EMNLP2023 #WMT #neuralEmpty #LLMs

#נלפ #תרגום #תעתיק .#HumanLevelTranslation #transliteration #neuralempty

#נלפ #תרגום.#HumanLevelTranslation #neuralempty

[1/8] Our new work (w/ @AriannaBisazza @gchrupala @MalvinaNissim) is finally out! 🎉. We introduce PECoRe, an interpretability framework using model internals to identify & attribute context dependence in language models. 📄Paper: #NLProc #neuralempty

#HumanLevelTranslation #neuralempty.#תרגוםמכונה #נלפ

Hebrew-English-French transliteration delicatessen . #HumanLevelTranslation #neuralempty #nlproc .#נלפ

We are not edible > We want. A shrubbery!. #HumanLevelTranslation (of biblical text, nothing new / productive).#neuralempty .#NLProc

Just when you thought physical #LanguageLearning books are more dependent than #llm. #emptyneuron #neuralempty.

Manly takbaru . #neuralempty #HumanLevelTranslation #nlproc

We need to make those grey rows (closed systems and non-transparent open weights) go down and put white rows up!. #nlposs #nlproc #neuralempty. But even the top white row, the base model used is non-transparent (llama) 🥺. What if we have open trillion tokens level MT datasets?

MTMA'23 Day 2. Starting with a talk by Marine Carpuat from UMD on Hallucinations in NMT. Slides (for all talks, uploading as we go) here: #neuralempty #nlproc

שלום כיתה #נלפ א1.כמה גורמים אפשריים לדעתכם לכישלון המפואר הזה?. #תרגום #בלשנות .#HumanLevelTranslation #neuralempty #NLProc

A strange skill that I've developed over the past few years of attending conferences is reading paper names on posters starting from the colon (or question mark?) onwards #EMNLP2024 #EMNLP2025 #adblock #neuralempty #emptyneuron

Magical model at @Unbabel does this #neuralempty. - There is no Thai as supported language in the UI.- Lets put it in the prompt.- Voila! . #emnlp2024 #wmt2024

Few-shot learning almost reaches traditional machine translation. Xavier Garcia @whybansal @ColinCherry George Foster, Maxim Krikun @fengfangxiaoyu @melvinjohnsonp @orf_bnw.#enough2skim #NLProc #neuralEmpty

pretty awesome stuff from #neuralempty folks.

I thought I had more than a decent grasp of machine translation, but this “waste of time” is a creepy mystery to me. #nlproc #HumanLevelTranslation #neuralempty