@inproceedings{marton-sayeed-2022-thematic,
title = "Thematic Fit Bits: Annotation Quality and Quantity Interplay for Event Participant Representation",
author = "Marton, Yuval and
Sayeed, Asad",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.556",
pages = "5188--5197",
abstract = "Modeling thematic fit (a verb-argument compositional semantics task) currently requires a very large burden of labeled data. We take a linguistically machine-annotated large corpus and replace corpus layers with output from higher-quality, more modern taggers. We compare the old and new corpus versions{'} impact on a verb-argument fit modeling task, using a high-performing neural approach. We discover that higher annotation quality dramatically reduces our data requirement while demonstrating better supervised predicate-argument classification. But in applying the model to psycholinguistic tasks outside the training objective, we see clear gains at scale, but only in one of two thematic fit estimation tasks, and no clear gains on the other. We also see that quality improves with training size, but perhaps plateauing or even declining in one task. Last, we tested the effect of role set size. All this suggests that the quality/quantity interplay is not all you need. We replicate previous studies while modifying certain role representation details and set a new state-of-the-art in event modeling, using a fraction of the data. We make the new corpus version public.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marton-sayeed-2022-thematic">
<titleInfo>
<title>Thematic Fit Bits: Annotation Quality and Quantity Interplay for Event Participant Representation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuval</namePart>
<namePart type="family">Marton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asad</namePart>
<namePart type="family">Sayeed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Modeling thematic fit (a verb-argument compositional semantics task) currently requires a very large burden of labeled data. We take a linguistically machine-annotated large corpus and replace corpus layers with output from higher-quality, more modern taggers. We compare the old and new corpus versions’ impact on a verb-argument fit modeling task, using a high-performing neural approach. We discover that higher annotation quality dramatically reduces our data requirement while demonstrating better supervised predicate-argument classification. But in applying the model to psycholinguistic tasks outside the training objective, we see clear gains at scale, but only in one of two thematic fit estimation tasks, and no clear gains on the other. We also see that quality improves with training size, but perhaps plateauing or even declining in one task. Last, we tested the effect of role set size. All this suggests that the quality/quantity interplay is not all you need. We replicate previous studies while modifying certain role representation details and set a new state-of-the-art in event modeling, using a fraction of the data. We make the new corpus version public.</abstract>
<identifier type="citekey">marton-sayeed-2022-thematic</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.556</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5188</start>
<end>5197</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thematic Fit Bits: Annotation Quality and Quantity Interplay for Event Participant Representation
%A Marton, Yuval
%A Sayeed, Asad
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F marton-sayeed-2022-thematic
%X Modeling thematic fit (a verb-argument compositional semantics task) currently requires a very large burden of labeled data. We take a linguistically machine-annotated large corpus and replace corpus layers with output from higher-quality, more modern taggers. We compare the old and new corpus versions’ impact on a verb-argument fit modeling task, using a high-performing neural approach. We discover that higher annotation quality dramatically reduces our data requirement while demonstrating better supervised predicate-argument classification. But in applying the model to psycholinguistic tasks outside the training objective, we see clear gains at scale, but only in one of two thematic fit estimation tasks, and no clear gains on the other. We also see that quality improves with training size, but perhaps plateauing or even declining in one task. Last, we tested the effect of role set size. All this suggests that the quality/quantity interplay is not all you need. We replicate previous studies while modifying certain role representation details and set a new state-of-the-art in event modeling, using a fraction of the data. We make the new corpus version public.
%U https://aclanthology.org/2022.lrec-1.556
%P 5188-5197
Markdown (Informal)
[Thematic Fit Bits: Annotation Quality and Quantity Interplay for Event Participant Representation](https://aclanthology.org/2022.lrec-1.556) (Marton & Sayeed, LREC 2022)
ACL