Pith. sign in

REVIEW

Translate First Reorder Later: Leveraging Monotonicity in Semantic Parsing

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 2210.04878 v2 pith:7DAATKWR submitted 2022-10-10 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords parsingsemanticalignmentsapproachcompositionalconventionalfirstgeneralization
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Prior work in semantic parsing has shown that conventional seq2seq models fail at compositional generalization tasks. This limitation led to a resurgence of methods that model alignments between sentences and their corresponding meaning representations, either implicitly through latent variables or explicitly by taking advantage of alignment annotations. We take the second direction and propose TPOL, a two-step approach that first translates input sentences monotonically and then reorders them to obtain the correct output. This is achieved with a modular framework comprising a Translator and a Reorderer component. We test our approach on two popular semantic parsing datasets. Our experiments show that by means of the monotonic translations, TPOL can learn reliable lexico-logical patterns from aligned data, significantly improving compositional generalization both over conventional seq2seq models, as well as over other approaches that exploit gold alignments.

Discussion (0). Continue with ORCID to comment.

Pith tools