@inproceedings{alves-etal-2025-surprisal,
title = "Surprisal Dynamics for the Detection of Multi-Word Expressions in {E}nglish",
author = "Alves, Diego and
Bagdasarov, Sergei and
Teich, Elke",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-ijcnlp.72/",
pages = "1185--1194",
ISBN = "979-8-89176-303-6",
abstract = "This work examines the potential of surprisal slope as a feature for identifying multi-word expressions (MWEs) in English, leveraging token-level surprisal estimates from the GPT-2 language model. Evaluations on the DiMSUM and SemEval-2022 datasets reveal that surprisal slope provides moderate yet meaningful discriminative power with a trade-off between specificity and coverage: while high recall indicates that surprisal slope captures many true MWEs, the slightly lower precision reflects false positives, particularly for non-MWEs that follow formulaic patterns (e.g., adjective-noun or verb-pronoun structures). The method performs particularly well for conventionalized expressions, such as idiomatic bigrams in the SemEval-2022 corpus. Both idiomatic and literal usages of these bigrams exhibit negative slopes, with idiomatic instances generally showing a more pronounced decrease.Overall, surprisal slope offers a cognitively motivated and interpretable signal that complements existing MWE identification methods, particularly for conventionalized expressions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alves-etal-2025-surprisal">
<titleInfo>
<title>Surprisal Dynamics for the Detection of Multi-Word Expressions in English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Alves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergei</namePart>
<namePart type="family">Bagdasarov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elke</namePart>
<namePart type="family">Teich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</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">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-303-6</identifier>
</relatedItem>
<abstract>This work examines the potential of surprisal slope as a feature for identifying multi-word expressions (MWEs) in English, leveraging token-level surprisal estimates from the GPT-2 language model. Evaluations on the DiMSUM and SemEval-2022 datasets reveal that surprisal slope provides moderate yet meaningful discriminative power with a trade-off between specificity and coverage: while high recall indicates that surprisal slope captures many true MWEs, the slightly lower precision reflects false positives, particularly for non-MWEs that follow formulaic patterns (e.g., adjective-noun or verb-pronoun structures). The method performs particularly well for conventionalized expressions, such as idiomatic bigrams in the SemEval-2022 corpus. Both idiomatic and literal usages of these bigrams exhibit negative slopes, with idiomatic instances generally showing a more pronounced decrease.Overall, surprisal slope offers a cognitively motivated and interpretable signal that complements existing MWE identification methods, particularly for conventionalized expressions.</abstract>
<identifier type="citekey">alves-etal-2025-surprisal</identifier>
<location>
<url>https://aclanthology.org/2025.findings-ijcnlp.72/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>1185</start>
<end>1194</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Surprisal Dynamics for the Detection of Multi-Word Expressions in English
%A Alves, Diego
%A Bagdasarov, Sergei
%A Teich, Elke
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-303-6
%F alves-etal-2025-surprisal
%X This work examines the potential of surprisal slope as a feature for identifying multi-word expressions (MWEs) in English, leveraging token-level surprisal estimates from the GPT-2 language model. Evaluations on the DiMSUM and SemEval-2022 datasets reveal that surprisal slope provides moderate yet meaningful discriminative power with a trade-off between specificity and coverage: while high recall indicates that surprisal slope captures many true MWEs, the slightly lower precision reflects false positives, particularly for non-MWEs that follow formulaic patterns (e.g., adjective-noun or verb-pronoun structures). The method performs particularly well for conventionalized expressions, such as idiomatic bigrams in the SemEval-2022 corpus. Both idiomatic and literal usages of these bigrams exhibit negative slopes, with idiomatic instances generally showing a more pronounced decrease.Overall, surprisal slope offers a cognitively motivated and interpretable signal that complements existing MWE identification methods, particularly for conventionalized expressions.
%U https://aclanthology.org/2025.findings-ijcnlp.72/
%P 1185-1194
Markdown (Informal)
[Surprisal Dynamics for the Detection of Multi-Word Expressions in English](https://aclanthology.org/2025.findings-ijcnlp.72/) (Alves et al., Findings 2025)
ACL
- Diego Alves, Sergei Bagdasarov, and Elke Teich. 2025. Surprisal Dynamics for the Detection of Multi-Word Expressions in English. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 1185–1194, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.