@inproceedings{weller-di-marco-fraser-2024-analyzing,
title = "Analyzing the Understanding of Morphologically Complex Words in Large Language Models",
author = "Weller-Di Marco, Marion and
Fraser, Alexander",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.90/",
pages = "1009--1020",
abstract = "We empirically study the ability of a Large Language Model (gpt-3.5-turbo-instruct) to understand morphologically complex words. In our experiments, we looked at a variety of tasks to analyse German compounds with regard to compositional word formation and derivation, such as identifying the head noun of existing and novel compounds, identifying the shared verb stem between two words, or recognizing words constructed with inappropriately used derivation morphemes as invalid. Our results show that the language model is generally capable of solving most tasks, except for the task of identifying ill-formed word forms. While the model demonstrated a good overall understanding of complex words and their word-internal structure, the results also suggest that there is no formal knowledge of derivational rules, but rather an interpretation of the observed word parts to derive the meaning of a word."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weller-di-marco-fraser-2024-analyzing">
<titleInfo>
<title>Analyzing the Understanding of Morphologically Complex Words in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marion</namePart>
<namePart type="family">Weller-Di Marco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We empirically study the ability of a Large Language Model (gpt-3.5-turbo-instruct) to understand morphologically complex words. In our experiments, we looked at a variety of tasks to analyse German compounds with regard to compositional word formation and derivation, such as identifying the head noun of existing and novel compounds, identifying the shared verb stem between two words, or recognizing words constructed with inappropriately used derivation morphemes as invalid. Our results show that the language model is generally capable of solving most tasks, except for the task of identifying ill-formed word forms. While the model demonstrated a good overall understanding of complex words and their word-internal structure, the results also suggest that there is no formal knowledge of derivational rules, but rather an interpretation of the observed word parts to derive the meaning of a word.</abstract>
<identifier type="citekey">weller-di-marco-fraser-2024-analyzing</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.90/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1009</start>
<end>1020</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Analyzing the Understanding of Morphologically Complex Words in Large Language Models
%A Weller-Di Marco, Marion
%A Fraser, Alexander
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F weller-di-marco-fraser-2024-analyzing
%X We empirically study the ability of a Large Language Model (gpt-3.5-turbo-instruct) to understand morphologically complex words. In our experiments, we looked at a variety of tasks to analyse German compounds with regard to compositional word formation and derivation, such as identifying the head noun of existing and novel compounds, identifying the shared verb stem between two words, or recognizing words constructed with inappropriately used derivation morphemes as invalid. Our results show that the language model is generally capable of solving most tasks, except for the task of identifying ill-formed word forms. While the model demonstrated a good overall understanding of complex words and their word-internal structure, the results also suggest that there is no formal knowledge of derivational rules, but rather an interpretation of the observed word parts to derive the meaning of a word.
%U https://aclanthology.org/2024.lrec-main.90/
%P 1009-1020
Markdown (Informal)
[Analyzing the Understanding of Morphologically Complex Words in Large Language Models](https://aclanthology.org/2024.lrec-main.90/) (Weller-Di Marco & Fraser, LREC-COLING 2024)
ACL