@inproceedings{vladika-etal-2022-tum,
title = "{TUM} sebis at {G}erm{E}val 2022: A Hybrid Model Leveraging {G}aussian Processes and Fine-Tuned {XLM}-{R}o{BERT}a for {G}erman Text Complexity Analysis",
author = "Vladika, Juraj and
Meisenbacher, Stephen and
Matthes, Florian",
editor = {M{\"o}ller, Sebastian and
Mohtaj, Salar and
Naderi, Babak},
booktitle = "Proceedings of the GermEval 2022 Workshop on Text Complexity Assessment of German Text",
month = sep,
year = "2022",
address = "Potsdam, Germany",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.germeval-1.9",
pages = "51--56",
abstract = "The task of quantifying the complexity of written language presents an interesting endeavor, particularly in the opportunity that it presents for aiding language learners. In this pursuit, the question of what exactly about natural language contributes to its complexity (or lack thereof) is an interesting point of investigation. We propose a hybrid approach, utilizing shallow models to capture linguistic features, while leveraging a fine-tuned embedding model to encode the semantics of input text. By harmonizing these two methods, we achieve competitive scores in the given metric, and we demonstrate improvements over either singular method. In addition, we uncover the effectiveness of Gaussian processes in the training of shallow models for text complexity analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vladika-etal-2022-tum">
<titleInfo>
<title>TUM sebis at GermEval 2022: A Hybrid Model Leveraging Gaussian Processes and Fine-Tuned XLM-RoBERTa for German Text Complexity Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juraj</namePart>
<namePart type="family">Vladika</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Meisenbacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Matthes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the GermEval 2022 Workshop on Text Complexity Assessment of German Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Möller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salar</namePart>
<namePart type="family">Mohtaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Babak</namePart>
<namePart type="family">Naderi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Potsdam, Germany</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The task of quantifying the complexity of written language presents an interesting endeavor, particularly in the opportunity that it presents for aiding language learners. In this pursuit, the question of what exactly about natural language contributes to its complexity (or lack thereof) is an interesting point of investigation. We propose a hybrid approach, utilizing shallow models to capture linguistic features, while leveraging a fine-tuned embedding model to encode the semantics of input text. By harmonizing these two methods, we achieve competitive scores in the given metric, and we demonstrate improvements over either singular method. In addition, we uncover the effectiveness of Gaussian processes in the training of shallow models for text complexity analysis.</abstract>
<identifier type="citekey">vladika-etal-2022-tum</identifier>
<location>
<url>https://aclanthology.org/2022.germeval-1.9</url>
</location>
<part>
<date>2022-09</date>
<extent unit="page">
<start>51</start>
<end>56</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TUM sebis at GermEval 2022: A Hybrid Model Leveraging Gaussian Processes and Fine-Tuned XLM-RoBERTa for German Text Complexity Analysis
%A Vladika, Juraj
%A Meisenbacher, Stephen
%A Matthes, Florian
%Y Möller, Sebastian
%Y Mohtaj, Salar
%Y Naderi, Babak
%S Proceedings of the GermEval 2022 Workshop on Text Complexity Assessment of German Text
%D 2022
%8 September
%I Association for Computational Linguistics
%C Potsdam, Germany
%F vladika-etal-2022-tum
%X The task of quantifying the complexity of written language presents an interesting endeavor, particularly in the opportunity that it presents for aiding language learners. In this pursuit, the question of what exactly about natural language contributes to its complexity (or lack thereof) is an interesting point of investigation. We propose a hybrid approach, utilizing shallow models to capture linguistic features, while leveraging a fine-tuned embedding model to encode the semantics of input text. By harmonizing these two methods, we achieve competitive scores in the given metric, and we demonstrate improvements over either singular method. In addition, we uncover the effectiveness of Gaussian processes in the training of shallow models for text complexity analysis.
%U https://aclanthology.org/2022.germeval-1.9
%P 51-56
Markdown (Informal)
[TUM sebis at GermEval 2022: A Hybrid Model Leveraging Gaussian Processes and Fine-Tuned XLM-RoBERTa for German Text Complexity Analysis](https://aclanthology.org/2022.germeval-1.9) (Vladika et al., GermEval 2022)
ACL