Papers by Joseph Cornelius

2 papers
UZH@CRAFT-ST: a Sequence-labeling Approach to Concept Recognition (D19-57)

Copied to clipboard

Challenge: CRAFT shared task 2019: concept recognition using named entity recognition and normalization . a biLSTM-based network and a transformer system were used to tackle both tasks in a single model .
Approach: They propose two different neural approaches to concept recognition . they propose a BiLSTM-based network and a bioBERT-based system for NER and normalization .
Outcome: The proposed systems model the task as a sequence labeling problem.
BUST: Benchmark for the evaluation of detectors of LLM-Generated Text (2024.naacl-long)

Copied to clipboard

Challenge: Using the benchmark, we evaluated 5 detectors and found substantial performance variance across tasks.
Approach: They propose to evaluate detectors of texts generated by instruction-tuned large language models (LLMs) using a benchmark dataset, they evaluated 5 detectors and found substantial performance variance across tasks.
Outcome: The proposed benchmarks evaluated 5 detectors and found substantial performance variance across tasks.

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