REVIEW 2 cited by
Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
While mainstream machine learning methods are known to have limited ability to compositionally generalize, new architectures and techniques continue to be proposed to address this limitation. We investigate state-of-the-art techniques and architectures in order to assess their effectiveness in improving compositional generalization in semantic parsing tasks based on the SCAN and CFQ datasets. We show that masked language model (MLM) pre-training rivals SCAN-inspired architectures on primitive holdout splits. On a more complex compositional task, we show that pre-training leads to significant improvements in performance vs. comparable non-pre-trained models, whereas architectures proposed to encourage compositional generalization on SCAN or in the area of algorithm learning fail to lead to significant improvements. We establish a new state of the art on the CFQ compositional generalization benchmark using MLM pre-training together with an intermediate representation.
Forward citations
Cited by 2 Pith papers
-
CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era
CypherBench provides 11 Wikidata-derived property graphs and 10,000+ text-to-Cypher questions, and state-of-the-art LLMs currently answer only about 60% correctly.
-
Compositional Generalization Across Distributional Shifts with Sparse Tree Operations
Sparse Differentiable Tree Machine represents trees as sparse coordinate lists, enabling efficient tree operations via bit-shifts and extending the Differentiable Tree Machine to sequence-to-sequence tasks with strong...
Discussion (0). Continue with ORCID to comment.