Grounded Graph Decoding improves Compositional Generalization in Question Answering

Yu Gai, Paras Jain, Wendi Zhang, Joseph Gonzalez, Dawn Song, Ion Stoica


Abstract
Question answering models struggle to generalize to novel compositions of training patterns. Current end-to-end models learn a flat input embedding which can lose input syntax context. Prior approaches improve generalization by learning permutation invariant models, but these methods do not scale to more complex train-test splits. We propose Grounded Graph Decoding, a method to improve compositional generalization of language representations by grounding structured predictions with an attention mechanism. Grounding enables the model to retain syntax information from the input that significantly improves generalization to complex inputs. By predicting a structured graph containing conjunctions of query clauses, we learn a group invariant representation without making assumptions on the target domain. Our model performs competitively on the Compositional Freebase Questions (CFQ) dataset, a challenging benchmark for compositional generalization in question answering. Especially, our model effectively solves the MCD1 split with 98% accuracy. All source is available at https://github.com/gaiyu0/cfq.
Anthology ID:
2021.findings-emnlp.157
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venues:
EMNLP | Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1829–1838
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.157
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.157.pdf
Data
CFQSCAN