Papers › Translate First Reorder Later: Leveraging Monotonicity in Semantic Parsing

Translate First Reorder Later: Leveraging Monotonicity in Semantic Parsing

10 Oct 2022arXiv:2210.04878archive 2025-07-28

Francesco Cazzaro, Davide Locatelli, Ariadna Quattoni, Xavier Carreras

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

interact-erc/tpol officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Semantic Parsing

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

LSTMSeq2SeqSigmoid ActivationTanh ActivationTest

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections