In the lead up to #ALTA2024, we're highlighting excellent talks and papers from previous ALTA events.
Here, listen to a #Keynote presentation from #ALTA2023 by Professor Heng Ji from #UniversityOfIllinois Urbana-Champaign, speaking to the #SmartBook - an #AI prophetess for disaster reporting and forecasting.
In this insightful talk, Professor Heng shows us how #NLP techniques provide better decision making tools.
In the lead up to #ALTA2024
we're highlighting excellent talks and papers from previous ALTA events.
This paper, from Vlada Rozova, Jinghui Liu, and Mike Conway at #UniMelb from #ALTA2023, applies #NLP to help solve problems of ambiguity and complexity in #medical#clinical data.
This paper also formed part of the informative #tutorial series at #ALTA2023.
Here, the ChatGPT C-LARA-Instance, Belinda Chiera, Cathy Chua, Chadi Raheb, Manny Rayner, Annika Simonsen, Zhengkang Xiang, and Rina Zviel-Girshin use the #OpenSource#CLARA platform to evaluate #GPT4's ability to perform #linguistics#NLP tasks such as #segmentation, #lemmatization and #glossing.
They should be related to a #language#technology task, able to be automatically evaluated, with training and test #data able to be distributed to participants at low- or no-cost, and should be fun!
While you consider submitting to the Call for Problems for the #ALTA2024 Shared Task (see link below), we'd like to share with you the winner of the #ALTA2023 Shared Task, which involved distinguishing #LLM-generated from human-generated text.
Here, Rinaldo Gagiano and Lin Tian from #RMIT use a fine-tuned #Falcon7B model with label smoothing, yielding an accuracy of 99.91%. Well done!
They should be related to a #language#technology task, able to be automatically evaluated, with training and test #data able to be distributed to participants at low- or no-cost, and should be fun!
While you're thinking about what to submit to the Call for Problems for the #ALTA2024 Shared Task (link below), we're sharing with you the 2nd-place winner of the #ALTA2023 Shared Task, where participants distinguished between #LLM-generated and human-generated text.