Table 7

Comparison of classification accuracy (%) and number of trainable parameters (N) for the methods without and with additional few-shot unsupervised domain adaptation (UDA) where number of shots is set as 4 and 8. Length of soft prompt is fixed as 10. MoE-Tr [42] is included in the comparison. Notably, MoE-Tr requires a large-scaled trainable model and needs multiple PLMs. MSP is parameter efficient and involves only one PLM. Various domains in Amazon review dataset are evaluated.

DomainMoE-TrSPMSPSP (4)MSP (4)MSP (8)
Books90.087.588.687.988.789.0
DVD89.386.286.987.088.588.1
Electronics90.687.488.487.989.290.3
Kitchen90.888.589.889.290.590.7
UDAyesnonoyesyesyes
N264M7.68K7.68K7.68K7.68K7.68K

or Create an Account

Close Modal
Close Modal