Pith. sign in

REVIEW 2 cited by

Structural generalization is hard for sequence-to-sequence models

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

arxiv 2210.13050 v1 pith:2J7PE6IY submitted 2022-10-24 cs.CL

classification cs.CL
keywords modelslinguisticseq2seqgeneralizationlimitationparsingsequence-to-sequencetasks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Sequence-to-sequence (seq2seq) models have been successful across many NLP tasks, including ones that require predicting linguistic structure. However, recent work on compositional generalization has shown that seq2seq models achieve very low accuracy in generalizing to linguistic structures that were not seen in training. We present new evidence that this is a general limitation of seq2seq models that is present not just in semantic parsing, but also in syntactic parsing and in text-to-text tasks, and that this limitation can often be overcome by neurosymbolic models that have linguistic knowledge built in. We further report on some experiments that give initial answers on the reasons for these limitations.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Randomly Sampled Language Reasoning Problems Elucidate Limitations of In-Context Learning

    cs.LG 2025-01 conditional novelty 6.0 of 10

    On randomly sampled 3-state DFA language tasks, foundation LLMs underperform n-gram baselines under pure in-context-learning prompts.

  2. Infusing Prompts with Syntax and Semantics

    cs.CL 2024-12 conditional novelty 6.0 of 10

    Appending syntactic and semantic analyses to prompts improves text-to-SQL accuracy in four low-resource languages and speeds fine-tuning.

Pith tools