@inproceedings{strakova-etal-2023-extending,
title = "Extending an Event-type Ontology: Adding Verbs and Classes Using Fine-tuned {LLM}s Suggestions",
author = "Strakov{\'a}, Jana and
Fu{\v{c}}{\'\i}kov{\'a}, Eva and
Haji{\v{c}}, Jan and
Ure{\v{s}}ov{\'a}, Zde{\v{n}}ka",
editor = "Prange, Jakob and
Friedrich, Annemarie",
booktitle = "Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.law-1.9",
doi = "10.18653/v1/2023.law-1.9",
pages = "85--95",
abstract = "In this project, we have investigated the use of advanced machine learning methods, specifically fine-tuned large language models, for pre-annotating data for a lexical extension task, namely adding descriptive words (verbs) to an existing (but incomplete, as of yet) ontology of event types. Several research questions have been focused on, from the investigation of a possible heuristics to provide at least hints to annotators which verbs to include and which are outside the current version of the ontology, to the possible use of the automatic scores to help the annotators to be more efficient in finding a threshold for identifying verbs that cannot be assigned to any existing class and therefore they are to be used as seeds for a new class. We have also carefully examined the correlation of the automatic scores with the human annotation. While the correlation turned out to be strong, its influence on the annotation proper is modest due to its near linearity, even though the mere fact of such pre-annotation leads to relatively short annotation times.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="strakova-etal-2023-extending">
<titleInfo>
<title>Extending an Event-type Ontology: Adding Verbs and Classes Using Fine-tuned LLMs Suggestions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jana</namePart>
<namePart type="family">Straková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Fučíková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Hajič</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zdeňka</namePart>
<namePart type="family">Urešová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakob</namePart>
<namePart type="family">Prange</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annemarie</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this project, we have investigated the use of advanced machine learning methods, specifically fine-tuned large language models, for pre-annotating data for a lexical extension task, namely adding descriptive words (verbs) to an existing (but incomplete, as of yet) ontology of event types. Several research questions have been focused on, from the investigation of a possible heuristics to provide at least hints to annotators which verbs to include and which are outside the current version of the ontology, to the possible use of the automatic scores to help the annotators to be more efficient in finding a threshold for identifying verbs that cannot be assigned to any existing class and therefore they are to be used as seeds for a new class. We have also carefully examined the correlation of the automatic scores with the human annotation. While the correlation turned out to be strong, its influence on the annotation proper is modest due to its near linearity, even though the mere fact of such pre-annotation leads to relatively short annotation times.</abstract>
<identifier type="citekey">strakova-etal-2023-extending</identifier>
<identifier type="doi">10.18653/v1/2023.law-1.9</identifier>
<location>
<url>https://aclanthology.org/2023.law-1.9</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>85</start>
<end>95</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extending an Event-type Ontology: Adding Verbs and Classes Using Fine-tuned LLMs Suggestions
%A Straková, Jana
%A Fučíková, Eva
%A Hajič, Jan
%A Urešová, Zdeňka
%Y Prange, Jakob
%Y Friedrich, Annemarie
%S Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F strakova-etal-2023-extending
%X In this project, we have investigated the use of advanced machine learning methods, specifically fine-tuned large language models, for pre-annotating data for a lexical extension task, namely adding descriptive words (verbs) to an existing (but incomplete, as of yet) ontology of event types. Several research questions have been focused on, from the investigation of a possible heuristics to provide at least hints to annotators which verbs to include and which are outside the current version of the ontology, to the possible use of the automatic scores to help the annotators to be more efficient in finding a threshold for identifying verbs that cannot be assigned to any existing class and therefore they are to be used as seeds for a new class. We have also carefully examined the correlation of the automatic scores with the human annotation. While the correlation turned out to be strong, its influence on the annotation proper is modest due to its near linearity, even though the mere fact of such pre-annotation leads to relatively short annotation times.
%R 10.18653/v1/2023.law-1.9
%U https://aclanthology.org/2023.law-1.9
%U https://doi.org/10.18653/v1/2023.law-1.9
%P 85-95
Markdown (Informal)
[Extending an Event-type Ontology: Adding Verbs and Classes Using Fine-tuned LLMs Suggestions](https://aclanthology.org/2023.law-1.9) (Straková et al., LAW 2023)
ACL