TY - JOUR
T1 - Erratum
T2 - ‘‘blimp: The benchmark of linguistic minimal pairs for english’’
AU - Warstadt, Alex
AU - Parrish, Alicia
AU - Liu, Haokun
AU - Mohananey, Anhad
AU - Peng, Wei
AU - Wang, Sheng Fu
AU - Bowman, Samuel R.
N1 - Publisher Copyright:
© 2020 Association for Computational Linguistics.
PY - 2020
Y1 - 2020
N2 - We correct wrongly reported results on BLiMP. We wrongly reported some results on BLiMP. The error does not change any of our conclusions in the paper. We made the following changes: 1. We corrected 12 values reported in Table 3 of the paper, shown in Table 1 of this statement. 2. In Section 5.1 of the paper, we wrote, ‘‘Only GPT-2 performs well above chance, and it remains 20 points below humans.’’ The corrected version reads ‘‘Only GPT-2 performs well above chance, and it remains 14 points below humans.’’ 3. We updated Figure 2 in the paper to reflect the updated results. These errors resulted from the erroneous inclusion in our calculations of the final results of two paradigms that we had eliminated from the dataset. These paradigms had been eliminated due to low human agreement with the labels. They belonged to the FILLER-GAP and ISLAND EFFECTS phenomena, respectively. Thus, only results for these phenomena and the overall results are affected.
AB - We correct wrongly reported results on BLiMP. We wrongly reported some results on BLiMP. The error does not change any of our conclusions in the paper. We made the following changes: 1. We corrected 12 values reported in Table 3 of the paper, shown in Table 1 of this statement. 2. In Section 5.1 of the paper, we wrote, ‘‘Only GPT-2 performs well above chance, and it remains 20 points below humans.’’ The corrected version reads ‘‘Only GPT-2 performs well above chance, and it remains 14 points below humans.’’ 3. We updated Figure 2 in the paper to reflect the updated results. These errors resulted from the erroneous inclusion in our calculations of the final results of two paradigms that we had eliminated from the dataset. These paradigms had been eliminated due to low human agreement with the labels. They belonged to the FILLER-GAP and ISLAND EFFECTS phenomena, respectively. Thus, only results for these phenomena and the overall results are affected.
UR - http://www.scopus.com/inward/record.url?scp=85108284500&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85108284500&partnerID=8YFLogxK
U2 - 10.1162/tacl_x_00375
DO - 10.1162/tacl_x_00375
M3 - Article
AN - SCOPUS:85108284500
SN - 2307-387X
VL - 8
SP - 867
EP - 868
JO - Transactions of the Association for Computational Linguistics
JF - Transactions of the Association for Computational Linguistics
ER -