Few-shot learning almost reaches traditional machine translation

https://arxiv.org/abs/2302.01398
#enough2skim #NLProc #neuralEmpty

3 reasons for hallucinations started
only 2 prevailed

Finding how networks behave while hallucinating, they
filter hallucinations (with great success)

https://arxiv.org/abs/2301.07779
#NLProc #neuralEmpty #NLP #deepRead

In my latest blog post https://jlibovicky.github.io/2023/01/19/Why-Dont-People-Use-Character-level-MT.html, I look back at a paper on character-level machine translation https://aclanthology.org/2022.findings-acl.194 that I finished over a year ago. #NeuralEmpty #NLProc

Bold statement (need to think about it more), especially when coming from a machine translation person.

I’d claim MT was no less revolutionary once it became pervasive in industry. But @marian_nmt seems to dismiss it now given ChatGPT

https://twitter.com/marian_nmt/status/1605956605475901456

#NLP #NLProc #neuralempty #NMT

@ #conll #EMNLP talk to me about
ColD Fusion & https://ibm.github.io/model-recycling/
BabyLM shared task
https://www.label-sleuth.org/
Enhancing decoders with syntax

And guided work (talk to them too)
Estimating #neuralEmpty quality with source only
Controlling structure in - neuron level
Details:

A brief overview 🗞️ of what I found most interesting on arXiv in November is now on my blog https://jlibovicky.github.io/2022/12/02/MTML-Highlights-November.html (just four papers this month 🤷‍♂️) #NLProc #NeuralEmpty #MTMLHighlights