| 1 |
Compositional Generalization Requires Compositional Parsers ...
|
|
|
|
Abstract:
A rapidly growing body of research on compositional generalization investigates the ability of a semantic parser to dynamically recombine linguistic elements seen in training into unseen sequences. We present a systematic comparison of sequence-to-sequence models and models guided by compositional principles on the recent COGS corpus (Kim and Linzen, 2020). Though seq2seq models can perform well on lexical tasks, they perform with near-zero accuracy on structural generalization tasks that require novel syntactic structures; this holds true even when they are trained to predict syntax instead of semantics. In contrast, compositional models achieve near-perfect accuracy on structural generalization; we present new results confirming this from the AM parser (Groschwitz et al., 2021). Our findings show structural generalization is a key measure of compositional generalization and requires models that are aware of complex structure. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2202.11937
https://dx.doi.org/10.48550/arxiv.2202.11937
|
|
BASE
|
|
Hide details
|
|
|
|
|
