@inproceedings{hofmann-etal-2020-individual,
title = "Individual corpora predict fast memory retrieval during reading",
author = {Hofmann, Markus J. and
M{\"u}ller, Lara and
R{\"o}lke, Andre and
Radach, Ralph and
Biemann, Chris},
booktitle = "Proceedings of the Workshop on the Cognitive Aspects of the Lexicon",
month = dec,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.cogalex-1.1",
pages = "1--11",
abstract = "The corpus, from which a predictive language model is trained, can be considered the experience of a semantic system. We recorded everyday reading of two participants for two months on a tablet, generating individual corpus samples of 300/500K tokens. Then we trained word2vec models from individual corpora and a 70 million-sentence newspaper corpus to obtain individual and norm-based long-term memory structure. To test whether individual corpora can make better predictions for a cognitive task of long-term memory retrieval, we generated stimulus materials consisting of 134 sentences with uncorrelated individual and norm-based word probabilities. For the subsequent eye tracking study 1-2 months later, our regression analyses revealed that individual, but not norm-corpus-based word probabilities can account for first-fixation duration and first-pass gaze duration. Word length additionally affected gaze duration and total viewing duration. The results suggest that corpora representative for an individual{'}s long-term memory structure can better explain reading performance than a norm corpus, and that recently acquired information is lexically accessed rapidly.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hofmann-etal-2020-individual">
<titleInfo>
<title>Individual corpora predict fast memory retrieval during reading</title>
</titleInfo>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Hofmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lara</namePart>
<namePart type="family">Müller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Rölke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ralph</namePart>
<namePart type="family">Radach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Biemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-dec</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on the Cognitive Aspects of the Lexicon</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The corpus, from which a predictive language model is trained, can be considered the experience of a semantic system. We recorded everyday reading of two participants for two months on a tablet, generating individual corpus samples of 300/500K tokens. Then we trained word2vec models from individual corpora and a 70 million-sentence newspaper corpus to obtain individual and norm-based long-term memory structure. To test whether individual corpora can make better predictions for a cognitive task of long-term memory retrieval, we generated stimulus materials consisting of 134 sentences with uncorrelated individual and norm-based word probabilities. For the subsequent eye tracking study 1-2 months later, our regression analyses revealed that individual, but not norm-corpus-based word probabilities can account for first-fixation duration and first-pass gaze duration. Word length additionally affected gaze duration and total viewing duration. The results suggest that corpora representative for an individual’s long-term memory structure can better explain reading performance than a norm corpus, and that recently acquired information is lexically accessed rapidly.</abstract>
<identifier type="citekey">hofmann-etal-2020-individual</identifier>
<location>
<url>https://aclanthology.org/2020.cogalex-1.1</url>
</location>
<part>
<date>2020-dec</date>
<extent unit="page">
<start>1</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Individual corpora predict fast memory retrieval during reading
%A Hofmann, Markus J.
%A Müller, Lara
%A Rölke, Andre
%A Radach, Ralph
%A Biemann, Chris
%S Proceedings of the Workshop on the Cognitive Aspects of the Lexicon
%D 2020
%8 dec
%I Association for Computational Linguistics
%C Online
%F hofmann-etal-2020-individual
%X The corpus, from which a predictive language model is trained, can be considered the experience of a semantic system. We recorded everyday reading of two participants for two months on a tablet, generating individual corpus samples of 300/500K tokens. Then we trained word2vec models from individual corpora and a 70 million-sentence newspaper corpus to obtain individual and norm-based long-term memory structure. To test whether individual corpora can make better predictions for a cognitive task of long-term memory retrieval, we generated stimulus materials consisting of 134 sentences with uncorrelated individual and norm-based word probabilities. For the subsequent eye tracking study 1-2 months later, our regression analyses revealed that individual, but not norm-corpus-based word probabilities can account for first-fixation duration and first-pass gaze duration. Word length additionally affected gaze duration and total viewing duration. The results suggest that corpora representative for an individual’s long-term memory structure can better explain reading performance than a norm corpus, and that recently acquired information is lexically accessed rapidly.
%U https://aclanthology.org/2020.cogalex-1.1
%P 1-11
Markdown (Informal)
[Individual corpora predict fast memory retrieval during reading](https://aclanthology.org/2020.cogalex-1.1) (Hofmann et al., CogALex 2020)
ACL