@inproceedings{rambelli-etal-2023-frequent,
title = "Are Frequent Phrases Directly Retrieved like Idioms? An Investigation with Self-Paced Reading and Language Models",
author = "Rambelli, Giulia and
Chersoni, Emmanuele and
Senaldi, Marco S. G. and
Blache, Philippe and
Lenci, Alessandro",
editor = "Bhatia, Archna and
Evang, Kilian and
Garcia, Marcos and
Giouli, Voula and
Han, Lifeng and
Taslimipoor, Shiva",
booktitle = "Proceedings of the 19th Workshop on Multiword Expressions (MWE 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.mwe-1.13",
doi = "10.18653/v1/2023.mwe-1.13",
pages = "87--98",
abstract = "An open question in language comprehension studies is whether non-compositional multiword expressions like idioms and compositional-but-frequent word sequences are processed differently. Are the latter constructed online, or are instead directly retrieved from the lexicon, with a degree of entrenchment depending on their frequency? In this paper, we address this question with two different methodologies. First, we set up a self-paced reading experiment comparing human reading times for idioms and both highfrequency and low-frequency compositional word sequences. Then, we ran the same experiment using the Surprisal metrics computed with Neural Language Models (NLMs). Our results provide evidence that idiomatic and high-frequency compositional expressions are processed similarly by both humans and NLMs. Additional experiments were run to test the possible factors that could affect the NLMs{'} performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rambelli-etal-2023-frequent">
<titleInfo>
<title>Are Frequent Phrases Directly Retrieved like Idioms? An Investigation with Self-Paced Reading and Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giulia</namePart>
<namePart type="family">Rambelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuele</namePart>
<namePart type="family">Chersoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="given">S</namePart>
<namePart type="given">G</namePart>
<namePart type="family">Senaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Workshop on Multiword Expressions (MWE 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Archna</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kilian</namePart>
<namePart type="family">Evang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Voula</namePart>
<namePart type="family">Giouli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiva</namePart>
<namePart type="family">Taslimipoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>An open question in language comprehension studies is whether non-compositional multiword expressions like idioms and compositional-but-frequent word sequences are processed differently. Are the latter constructed online, or are instead directly retrieved from the lexicon, with a degree of entrenchment depending on their frequency? In this paper, we address this question with two different methodologies. First, we set up a self-paced reading experiment comparing human reading times for idioms and both highfrequency and low-frequency compositional word sequences. Then, we ran the same experiment using the Surprisal metrics computed with Neural Language Models (NLMs). Our results provide evidence that idiomatic and high-frequency compositional expressions are processed similarly by both humans and NLMs. Additional experiments were run to test the possible factors that could affect the NLMs’ performance.</abstract>
<identifier type="citekey">rambelli-etal-2023-frequent</identifier>
<identifier type="doi">10.18653/v1/2023.mwe-1.13</identifier>
<location>
<url>https://aclanthology.org/2023.mwe-1.13</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>87</start>
<end>98</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Are Frequent Phrases Directly Retrieved like Idioms? An Investigation with Self-Paced Reading and Language Models
%A Rambelli, Giulia
%A Chersoni, Emmanuele
%A Senaldi, Marco S. G.
%A Blache, Philippe
%A Lenci, Alessandro
%Y Bhatia, Archna
%Y Evang, Kilian
%Y Garcia, Marcos
%Y Giouli, Voula
%Y Han, Lifeng
%Y Taslimipoor, Shiva
%S Proceedings of the 19th Workshop on Multiword Expressions (MWE 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F rambelli-etal-2023-frequent
%X An open question in language comprehension studies is whether non-compositional multiword expressions like idioms and compositional-but-frequent word sequences are processed differently. Are the latter constructed online, or are instead directly retrieved from the lexicon, with a degree of entrenchment depending on their frequency? In this paper, we address this question with two different methodologies. First, we set up a self-paced reading experiment comparing human reading times for idioms and both highfrequency and low-frequency compositional word sequences. Then, we ran the same experiment using the Surprisal metrics computed with Neural Language Models (NLMs). Our results provide evidence that idiomatic and high-frequency compositional expressions are processed similarly by both humans and NLMs. Additional experiments were run to test the possible factors that could affect the NLMs’ performance.
%R 10.18653/v1/2023.mwe-1.13
%U https://aclanthology.org/2023.mwe-1.13
%U https://doi.org/10.18653/v1/2023.mwe-1.13
%P 87-98
Markdown (Informal)
[Are Frequent Phrases Directly Retrieved like Idioms? An Investigation with Self-Paced Reading and Language Models](https://aclanthology.org/2023.mwe-1.13) (Rambelli et al., MWE 2023)
ACL