@inproceedings{katrapati-shrivastava-2025-constructions,
title = "Can Constructions ``{SCAN}'' Compositionality ?",
author = "Katrapati, Ganesh and
Shrivastava, Manish",
editor = "Bonial, Claire and
Torgbi, Melissa and
Weissweiler, Leonie and
Blodgett, Austin and
Beuls, Katrien and
Van Eecke, Paul and
Tayyar Madabushi, Harish",
booktitle = "Proceedings of the Second International Workshop on Construction Grammars and NLP",
month = sep,
year = "2025",
address = {D{\"u}sseldorf, Germany},
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.cxgsnlp-1.17/",
pages = "165--171",
ISBN = "979-8-89176-318-0",
abstract = "Sequence to Sequence models struggle at compositionality and systematic generalisation even while they excel at many other tasks.We attribute this limitation to their failure to internalise constructions{---}conventionalised form{--}meaning pairings that license productive recombination. Building on these insights, we introduce an unsupervised procedure for mining pseudo-constructions: variable-slot templates automatically extracted from training data. When applied to the SCAN dataset, ourmethod yields large gains out-of-distribution splits: accuracy rises to 47.8{\%} on ADD JUMP and to 20.3{\%} on AROUND RIGHT without any architectural changes or additional supervision. The model also attains competitive performance with {\ensuremath{\leq}} 40{\%} of the original training data, demonstrating strong data efficiency. Our findings highlight the promise of construction-aware preprocessing as an alternative to heavy architectural or training-regime interventions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="katrapati-shrivastava-2025-constructions">
<titleInfo>
<title>Can Constructions “SCAN” Compositionality ?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ganesh</namePart>
<namePart type="family">Katrapati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manish</namePart>
<namePart type="family">Shrivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second International Workshop on Construction Grammars and NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Bonial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melissa</namePart>
<namePart type="family">Torgbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonie</namePart>
<namePart type="family">Weissweiler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Austin</namePart>
<namePart type="family">Blodgett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katrien</namePart>
<namePart type="family">Beuls</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Van Eecke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Düsseldorf, Germany</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-318-0</identifier>
</relatedItem>
<abstract>Sequence to Sequence models struggle at compositionality and systematic generalisation even while they excel at many other tasks.We attribute this limitation to their failure to internalise constructions—conventionalised form–meaning pairings that license productive recombination. Building on these insights, we introduce an unsupervised procedure for mining pseudo-constructions: variable-slot templates automatically extracted from training data. When applied to the SCAN dataset, ourmethod yields large gains out-of-distribution splits: accuracy rises to 47.8% on ADD JUMP and to 20.3% on AROUND RIGHT without any architectural changes or additional supervision. The model also attains competitive performance with \ensuremathłeq 40% of the original training data, demonstrating strong data efficiency. Our findings highlight the promise of construction-aware preprocessing as an alternative to heavy architectural or training-regime interventions.</abstract>
<identifier type="citekey">katrapati-shrivastava-2025-constructions</identifier>
<location>
<url>https://aclanthology.org/2025.cxgsnlp-1.17/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>165</start>
<end>171</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Constructions “SCAN” Compositionality ?
%A Katrapati, Ganesh
%A Shrivastava, Manish
%Y Bonial, Claire
%Y Torgbi, Melissa
%Y Weissweiler, Leonie
%Y Blodgett, Austin
%Y Beuls, Katrien
%Y Van Eecke, Paul
%Y Tayyar Madabushi, Harish
%S Proceedings of the Second International Workshop on Construction Grammars and NLP
%D 2025
%8 September
%I Association for Computational Linguistics
%C Düsseldorf, Germany
%@ 979-8-89176-318-0
%F katrapati-shrivastava-2025-constructions
%X Sequence to Sequence models struggle at compositionality and systematic generalisation even while they excel at many other tasks.We attribute this limitation to their failure to internalise constructions—conventionalised form–meaning pairings that license productive recombination. Building on these insights, we introduce an unsupervised procedure for mining pseudo-constructions: variable-slot templates automatically extracted from training data. When applied to the SCAN dataset, ourmethod yields large gains out-of-distribution splits: accuracy rises to 47.8% on ADD JUMP and to 20.3% on AROUND RIGHT without any architectural changes or additional supervision. The model also attains competitive performance with \ensuremathłeq 40% of the original training data, demonstrating strong data efficiency. Our findings highlight the promise of construction-aware preprocessing as an alternative to heavy architectural or training-regime interventions.
%U https://aclanthology.org/2025.cxgsnlp-1.17/
%P 165-171
Markdown (Informal)
[Can Constructions “SCAN” Compositionality ?](https://aclanthology.org/2025.cxgsnlp-1.17/) (Katrapati & Shrivastava, CxGsNLP 2025)
ACL
- Ganesh Katrapati and Manish Shrivastava. 2025. Can Constructions “SCAN” Compositionality ?. In Proceedings of the Second International Workshop on Construction Grammars and NLP, pages 165–171, Düsseldorf, Germany. Association for Computational Linguistics.