@inproceedings{sarti-etal-2021-looks,
title = "That Looks Hard: Characterizing Linguistic Complexity in Humans and Language Models",
author = "Sarti, Gabriele and
Brunato, Dominique and
Dell{'}Orletta, Felice",
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-1.5/",
doi = "10.18653/v1/2021.cmcl-1.5",
pages = "48--60",
abstract = "This paper investigates the relationship between two complementary perspectives in the human assessment of sentence complexity and how they are modeled in a neural language model (NLM). The first perspective takes into account multiple online behavioral metrics obtained from eye-tracking recordings. The second one concerns the offline perception of complexity measured by explicit human judgments. Using a broad spectrum of linguistic features modeling lexical, morpho-syntactic, and syntactic properties of sentences, we perform a comprehensive analysis of linguistic phenomena associated with the two complexity viewpoints and report similarities and differences. We then show the effectiveness of linguistic features when explicitly leveraged by a regression model for predicting sentence complexity and compare its results with the ones obtained by a fine-tuned neural language model. We finally probe the NLM`s linguistic competence before and after fine-tuning, highlighting how linguistic information encoded in representations changes when the model learns to predict complexity."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sarti-etal-2021-looks">
<titleInfo>
<title>That Looks Hard: Characterizing Linguistic Complexity in Humans and Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gabriele</namePart>
<namePart type="family">Sarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominique</namePart>
<namePart type="family">Brunato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</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 investigates the relationship between two complementary perspectives in the human assessment of sentence complexity and how they are modeled in a neural language model (NLM). The first perspective takes into account multiple online behavioral metrics obtained from eye-tracking recordings. The second one concerns the offline perception of complexity measured by explicit human judgments. Using a broad spectrum of linguistic features modeling lexical, morpho-syntactic, and syntactic properties of sentences, we perform a comprehensive analysis of linguistic phenomena associated with the two complexity viewpoints and report similarities and differences. We then show the effectiveness of linguistic features when explicitly leveraged by a regression model for predicting sentence complexity and compare its results with the ones obtained by a fine-tuned neural language model. We finally probe the NLM‘s linguistic competence before and after fine-tuning, highlighting how linguistic information encoded in representations changes when the model learns to predict complexity.</abstract>
<identifier type="citekey">sarti-etal-2021-looks</identifier>
<identifier type="doi">10.18653/v1/2021.cmcl-1.5</identifier>
<location>
<url>https://aclanthology.org/2021.cmcl-1.5/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>48</start>
<end>60</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T That Looks Hard: Characterizing Linguistic Complexity in Humans and Language Models
%A Sarti, Gabriele
%A Brunato, Dominique
%A Dell’Orletta, Felice
%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 sarti-etal-2021-looks
%X This paper investigates the relationship between two complementary perspectives in the human assessment of sentence complexity and how they are modeled in a neural language model (NLM). The first perspective takes into account multiple online behavioral metrics obtained from eye-tracking recordings. The second one concerns the offline perception of complexity measured by explicit human judgments. Using a broad spectrum of linguistic features modeling lexical, morpho-syntactic, and syntactic properties of sentences, we perform a comprehensive analysis of linguistic phenomena associated with the two complexity viewpoints and report similarities and differences. We then show the effectiveness of linguistic features when explicitly leveraged by a regression model for predicting sentence complexity and compare its results with the ones obtained by a fine-tuned neural language model. We finally probe the NLM‘s linguistic competence before and after fine-tuning, highlighting how linguistic information encoded in representations changes when the model learns to predict complexity.
%R 10.18653/v1/2021.cmcl-1.5
%U https://aclanthology.org/2021.cmcl-1.5/
%U https://doi.org/10.18653/v1/2021.cmcl-1.5
%P 48-60
Markdown (Informal)
[That Looks Hard: Characterizing Linguistic Complexity in Humans and Language Models](https://aclanthology.org/2021.cmcl-1.5/) (Sarti et al., CMCL 2021)
ACL