Token-length Bias in Minimal-pair Paradigm Datasets.

Naoya Ueda Masato Mita Teruaki Oka Mamoru Komachi

Published in: LREC/COLING (2024)

Keyphrases

minimal length
database
benchmark datasets
pairwise
uci machine learning repository
maximum number
data sets
data mining
trade off
raw data
synthetic datasets