@inproceedings{rozner-etal-2025-constructions,
title = "Constructions are Revealed in Word Distributions",
author = "Rozner, Joshua and
Weissweiler, Leonie and
Mahowald, Kyle and
Shain, Cory",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.108/",
pages = "2116--2138",
ISBN = "979-8-89176-332-6",
abstract = "Construction grammar posits that constructions, or form-meaning pairings, are acquired through experience with language (the distributional learning hypothesis).But how much information about constructions does this distribution actually contain? Corpus-based analyses provide some answers, but text alone cannot answer counterfactual questions about what caused a particular word to occur.This requires computable models of the distribution over strings{---}namely, pretrained language models (PLMs).Here, we treat a RoBERTa model as a proxy for this distribution and hypothesize that constructions will be revealed within it as patterns of statistical affinity.We support this hypothesis experimentally: many constructions are robustly distinguished, including (i) hard cases where semantically distinct constructions are superficially similar, as well as (ii) schematic constructions, whose ``slots'' can be filled by abstract word classes.Despite this success, we also provide qualitative evidence that statistical affinity alone may be insufficient to identify all constructions from text.Thus, statistical affinity is likely an important, but partial, signal available to learners."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rozner-etal-2025-constructions">
<titleInfo>
<title>Constructions are Revealed in Word Distributions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Rozner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonie</namePart>
<namePart type="family">Weissweiler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Mahowald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cory</namePart>
<namePart type="family">Shain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Construction grammar posits that constructions, or form-meaning pairings, are acquired through experience with language (the distributional learning hypothesis).But how much information about constructions does this distribution actually contain? Corpus-based analyses provide some answers, but text alone cannot answer counterfactual questions about what caused a particular word to occur.This requires computable models of the distribution over strings—namely, pretrained language models (PLMs).Here, we treat a RoBERTa model as a proxy for this distribution and hypothesize that constructions will be revealed within it as patterns of statistical affinity.We support this hypothesis experimentally: many constructions are robustly distinguished, including (i) hard cases where semantically distinct constructions are superficially similar, as well as (ii) schematic constructions, whose “slots” can be filled by abstract word classes.Despite this success, we also provide qualitative evidence that statistical affinity alone may be insufficient to identify all constructions from text.Thus, statistical affinity is likely an important, but partial, signal available to learners.</abstract>
<identifier type="citekey">rozner-etal-2025-constructions</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.108/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>2116</start>
<end>2138</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constructions are Revealed in Word Distributions
%A Rozner, Joshua
%A Weissweiler, Leonie
%A Mahowald, Kyle
%A Shain, Cory
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F rozner-etal-2025-constructions
%X Construction grammar posits that constructions, or form-meaning pairings, are acquired through experience with language (the distributional learning hypothesis).But how much information about constructions does this distribution actually contain? Corpus-based analyses provide some answers, but text alone cannot answer counterfactual questions about what caused a particular word to occur.This requires computable models of the distribution over strings—namely, pretrained language models (PLMs).Here, we treat a RoBERTa model as a proxy for this distribution and hypothesize that constructions will be revealed within it as patterns of statistical affinity.We support this hypothesis experimentally: many constructions are robustly distinguished, including (i) hard cases where semantically distinct constructions are superficially similar, as well as (ii) schematic constructions, whose “slots” can be filled by abstract word classes.Despite this success, we also provide qualitative evidence that statistical affinity alone may be insufficient to identify all constructions from text.Thus, statistical affinity is likely an important, but partial, signal available to learners.
%U https://aclanthology.org/2025.emnlp-main.108/
%P 2116-2138
Markdown (Informal)
[Constructions are Revealed in Word Distributions](https://aclanthology.org/2025.emnlp-main.108/) (Rozner et al., EMNLP 2025)
ACL
- Joshua Rozner, Leonie Weissweiler, Kyle Mahowald, and Cory Shain. 2025. Constructions are Revealed in Word Distributions. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 2116–2138, Suzhou, China. Association for Computational Linguistics.