@inproceedings{jon-bojar-2026-thesis,
title = "Thesis proposal: Are We Losing Textual Diversity to Natural Language Processing?",
author = "Jon, Josef and
Bojar, Ond{\v{r}}ej",
editor = "Baez Santamaria, Selene and
Somayajula, Sai Ashish and
Yamaguchi, Atsuki",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-srw.14/",
pages = "188--206",
ISBN = "979-8-89176-383-8",
abstract = "This thesis argues that the currently widely used Natural Language Processing algorithms possibly have various limitations related to the properties of the texts they handle and produce. With the wide adoption of these tools in rapid progress, we must ask what these limitations are and what are the possible implications of integrating such tools into our daily lives.As a testbed, we have chosen the task of Neural Machine Translation (NMT). Nevertheless, we aim for general insights and outcomes, applicable to current Large Language Models (LLMs). We ask whether the algorithms used in NMT have inherent inductive biases that are beneficial for most types of inputs but might harm the processing of untypical texts, thereby contributing to a cycle of monotonous, repetitive language {--} whether generated by machines or humans.To explore this hypothesis, we define a set of measures to quantify text diversity based on its statistical properties, like uniformity or rhythmicity of word-level surprisal, on multiple scales (sentence, discourse, language). We conduct a series of experiments to investigate whether NMT systems struggle with maintaining the diversity of such texts, potentially reducing the richness of the generated language, compared to human translators.We further analyze potential origins of these limitations within existing training objectives and decoding strategies. Ultimately, our goal is to propose and validate alternative approaches (e.g., loss functions, decoding algorithms) that maintain the diversity and complexity of language and that allow for better global planning of the output generation, enabling the models to better reflect the ambiguities inherent in human communication."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jon-bojar-2026-thesis">
<titleInfo>
<title>Thesis proposal: Are We Losing Textual Diversity to Natural Language Processing?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Jon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Selene</namePart>
<namePart type="family">Baez Santamaria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Ashish</namePart>
<namePart type="family">Somayajula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsuki</namePart>
<namePart type="family">Yamaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-383-8</identifier>
</relatedItem>
<abstract>This thesis argues that the currently widely used Natural Language Processing algorithms possibly have various limitations related to the properties of the texts they handle and produce. With the wide adoption of these tools in rapid progress, we must ask what these limitations are and what are the possible implications of integrating such tools into our daily lives.As a testbed, we have chosen the task of Neural Machine Translation (NMT). Nevertheless, we aim for general insights and outcomes, applicable to current Large Language Models (LLMs). We ask whether the algorithms used in NMT have inherent inductive biases that are beneficial for most types of inputs but might harm the processing of untypical texts, thereby contributing to a cycle of monotonous, repetitive language – whether generated by machines or humans.To explore this hypothesis, we define a set of measures to quantify text diversity based on its statistical properties, like uniformity or rhythmicity of word-level surprisal, on multiple scales (sentence, discourse, language). We conduct a series of experiments to investigate whether NMT systems struggle with maintaining the diversity of such texts, potentially reducing the richness of the generated language, compared to human translators.We further analyze potential origins of these limitations within existing training objectives and decoding strategies. Ultimately, our goal is to propose and validate alternative approaches (e.g., loss functions, decoding algorithms) that maintain the diversity and complexity of language and that allow for better global planning of the output generation, enabling the models to better reflect the ambiguities inherent in human communication.</abstract>
<identifier type="citekey">jon-bojar-2026-thesis</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-srw.14/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>188</start>
<end>206</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thesis proposal: Are We Losing Textual Diversity to Natural Language Processing?
%A Jon, Josef
%A Bojar, Ondřej
%Y Baez Santamaria, Selene
%Y Somayajula, Sai Ashish
%Y Yamaguchi, Atsuki
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-383-8
%F jon-bojar-2026-thesis
%X This thesis argues that the currently widely used Natural Language Processing algorithms possibly have various limitations related to the properties of the texts they handle and produce. With the wide adoption of these tools in rapid progress, we must ask what these limitations are and what are the possible implications of integrating such tools into our daily lives.As a testbed, we have chosen the task of Neural Machine Translation (NMT). Nevertheless, we aim for general insights and outcomes, applicable to current Large Language Models (LLMs). We ask whether the algorithms used in NMT have inherent inductive biases that are beneficial for most types of inputs but might harm the processing of untypical texts, thereby contributing to a cycle of monotonous, repetitive language – whether generated by machines or humans.To explore this hypothesis, we define a set of measures to quantify text diversity based on its statistical properties, like uniformity or rhythmicity of word-level surprisal, on multiple scales (sentence, discourse, language). We conduct a series of experiments to investigate whether NMT systems struggle with maintaining the diversity of such texts, potentially reducing the richness of the generated language, compared to human translators.We further analyze potential origins of these limitations within existing training objectives and decoding strategies. Ultimately, our goal is to propose and validate alternative approaches (e.g., loss functions, decoding algorithms) that maintain the diversity and complexity of language and that allow for better global planning of the output generation, enabling the models to better reflect the ambiguities inherent in human communication.
%U https://aclanthology.org/2026.eacl-srw.14/
%P 188-206
Markdown (Informal)
[Thesis proposal: Are We Losing Textual Diversity to Natural Language Processing?](https://aclanthology.org/2026.eacl-srw.14/) (Jon & Bojar, EACL 2026)
ACL