Papers by Lena Jurkschat

2 papers
Tokenizer Choice For LLM Training: Negligible or Crucial? (2024.findings-naacl)

Copied to clipboard

Challenge: Recent success of large language models has been driven by curating the training dataset composition, scaling of model architectures and advancements in pretraining objectives, leaving tokenizer influence as a blind spot.
Approach: They conduct a comprehensive study on the influence of tokenizer choice on LLM downstream performance by training 24 mono- and multilingual LLMs at a 2.6B parameter scale.
Outcome: The proposed model can significantly impact the model's downstream performance and training costs.
Few-Shot Learning for Argument Aspects of the Nuclear Energy Debate (2022.lrec-1)

Copied to clipboard

Challenge: Existing methods to classify aspects of arguments are expensive and require training data for further aspects and topics.
Approach: They propose a supervised aspect-based argument mining task to classify arguments into semantically coherent groups referring to the same defined aspect categories.
Outcome: The proposed method is able to predict share of arguments in a British newspaper corpus with 50 to 100 examples per aspect.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations