SUBS: Subtree Substitution for Compositional Semantic Parsing

Abstract

Although sequence-to-sequence models often achieve good performance in semantic parsing for i.i.d. data, their performance is still inferior in compositional generalization. Several data augmentation methods have been proposed to alleviate this problem. However, prior work only leveraged superficial grammar or rules for data augmentation, which resulted in limited improvement. We propose to use subtree substitution for compositional data augmentation, where we consider subtrees with similar semantic functions as exchangeable. Our experiments showed that such augmented data led to significantly better performance on SCAN and GEOQUERY, and reached new SOTA on compositional split of GEOQUERY. We have publicly released our code at https: //github.com/GT-SALT/SUBS .

SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models

“…Generally, one way to improve compositional generalizability is to incorporate inductive biases directly to models through moduler models (Dong and Lapata, 2018), symbolic-neural machines , latent variables/intermediate representations (Zheng and Lapata, 2020;, metalearning (Lake, 2019) etc. Another way is to first do data augmentation and then train a model with augmented data (Andreas, 2019;Zhong et al, 2020;Akyürek et al, 2020;Yang et al, 2022b). Pretrained models has also been shown useful for compositional semantic parsing (Oren et al, 2020;Furrer et al, 2020).…”