@inproceedings{rathi-2021-dependency,
title = "Dependency Locality and Neural Surprisal as Predictors of Processing Difficulty: Evidence from Reading Times",
author = "Rathi, Neil",
editor = "Chersoni, Emmanuele and
Hollenstein, Nora and
Jacobs, Cassandra and
Oseki, Yohei and
Pr{\'e}vot, Laurent and
Santus, Enrico",
booktitle = "Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.cmcl-1.21",
doi = "10.18653/v1/2021.cmcl-1.21",
pages = "171--176",
abstract = "This paper compares two influential theories of processing difficulty: Gibson (2000){'}s Dependency Locality Theory (DLT) and Hale (2001){'}s Surprisal Theory. While prior work has aimed to compare DLT and Surprisal Theory (see Demberg and Keller, 2008), they have not yet been compared using more modern and powerful methods for estimating surprisal and DLT integration cost. I compare estimated surprisal values from two models, an RNN and a Transformer neural network, as well as DLT integration cost from a hand-parsed treebank, to reading times from the Dundee Corpus. Our results for integration cost corroborate those of Demberg and Keller (2008), finding that it is a negative predictor of reading times overall and a strong positive predictor for nouns, but contrast with their observations for surprisal, finding strong evidence for lexicalized surprisal as a predictor of reading times. Ultimately, I conclude that a broad-coverage model must integrate both theories in order to most accurately predict processing difficulty.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rathi-2021-dependency">
<titleInfo>
<title>Dependency Locality and Neural Surprisal as Predictors of Processing Difficulty: Evidence from Reading Times</title>
</titleInfo>
<name type="personal">
<namePart type="given">Neil</namePart>
<namePart type="family">Rathi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emmanuele</namePart>
<namePart type="family">Chersoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Hollenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cassandra</namePart>
<namePart type="family">Jacobs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yohei</namePart>
<namePart type="family">Oseki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Prévot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper compares two influential theories of processing difficulty: Gibson (2000)’s Dependency Locality Theory (DLT) and Hale (2001)’s Surprisal Theory. While prior work has aimed to compare DLT and Surprisal Theory (see Demberg and Keller, 2008), they have not yet been compared using more modern and powerful methods for estimating surprisal and DLT integration cost. I compare estimated surprisal values from two models, an RNN and a Transformer neural network, as well as DLT integration cost from a hand-parsed treebank, to reading times from the Dundee Corpus. Our results for integration cost corroborate those of Demberg and Keller (2008), finding that it is a negative predictor of reading times overall and a strong positive predictor for nouns, but contrast with their observations for surprisal, finding strong evidence for lexicalized surprisal as a predictor of reading times. Ultimately, I conclude that a broad-coverage model must integrate both theories in order to most accurately predict processing difficulty.</abstract>
<identifier type="citekey">rathi-2021-dependency</identifier>
<identifier type="doi">10.18653/v1/2021.cmcl-1.21</identifier>
<location>
<url>https://aclanthology.org/2021.cmcl-1.21</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>171</start>
<end>176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dependency Locality and Neural Surprisal as Predictors of Processing Difficulty: Evidence from Reading Times
%A Rathi, Neil
%Y Chersoni, Emmanuele
%Y Hollenstein, Nora
%Y Jacobs, Cassandra
%Y Oseki, Yohei
%Y Prévot, Laurent
%Y Santus, Enrico
%S Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F rathi-2021-dependency
%X This paper compares two influential theories of processing difficulty: Gibson (2000)’s Dependency Locality Theory (DLT) and Hale (2001)’s Surprisal Theory. While prior work has aimed to compare DLT and Surprisal Theory (see Demberg and Keller, 2008), they have not yet been compared using more modern and powerful methods for estimating surprisal and DLT integration cost. I compare estimated surprisal values from two models, an RNN and a Transformer neural network, as well as DLT integration cost from a hand-parsed treebank, to reading times from the Dundee Corpus. Our results for integration cost corroborate those of Demberg and Keller (2008), finding that it is a negative predictor of reading times overall and a strong positive predictor for nouns, but contrast with their observations for surprisal, finding strong evidence for lexicalized surprisal as a predictor of reading times. Ultimately, I conclude that a broad-coverage model must integrate both theories in order to most accurately predict processing difficulty.
%R 10.18653/v1/2021.cmcl-1.21
%U https://aclanthology.org/2021.cmcl-1.21
%U https://doi.org/10.18653/v1/2021.cmcl-1.21
%P 171-176
Markdown (Informal)
[Dependency Locality and Neural Surprisal as Predictors of Processing Difficulty: Evidence from Reading Times](https://aclanthology.org/2021.cmcl-1.21) (Rathi, CMCL 2021)
ACL