@inproceedings{gupta2022structurally,
author = {Gupta, Shivanshu and Singh, Sameer and Gardner, Matt},
title = {Structurally Diverse Sampling Reduces Spurious Correlations in Semantic Parsing Datasets},
booktitle = {EMNLP 2022},
year = {2022},
month = {March},
abstract = {A rapidly growing body of research has demonstrated the inability of NLP models to generalize compositionally and has tried to alleviate it through specialized architectures, training schemes, and data augmentation, among other approaches. In this work, we study a different relatively under-explored approach: sampling diverse train sets that encourage compositional generalization. We propose a novel algorithm for sampling a structurally diverse set of instances from a labeled instance pool with structured outputs. Evaluating on 5 semantic parsing datasets of varying complexity, we show that our algorithm performs competitively with or better than prior algorithms in not only compositional template splits but also traditional IID splits of all but the least structurally diverse datasets. In general, we find that diverse train sets lead to better generalization than random training sets of the same size in 9 out of 10 dataset-split pairs, with over 10% absolute improvement in 5, providing further evidence to their sample efficiency. Moreover, we show that structural diversity also makes for more comprehensive test sets that require diverse training to succeed on. Finally, we use information theory to show that reduction in spurious correlations between substructures may be one reason why diverse training sets improve generalization.},
url = {http://approjects.co.za/?big=en-us/research/publication/structurally-diverse-sampling-reduces-spurious-correlations-in-semantic-parsing-datasets/},
}