BibTeX

@inProceedings{szawerna-etal-2024-detecting-336385,
	title        = {Detecting Personal Identifiable Information in Swedish Learner Essays},
	abstract     = {Linguistic data can — and often does — contain PII (Personal Identifiable Information). Both from a legal and ethical standpoint, the sharing of such data is not permissible. According to the GDPR, pseudonymization, i.e. the replacement of sensitive information with surrogates, is an acceptable strategy for privacy preservation. While research has been conducted on the detection and replacement of sensitive data in Swedish medical data using Large Language Models (LLMs), it is unclear whether these models handle PII in less structured and more thematically varied texts equally well. In this paper, we present and discuss the performance of an LLM-based PII-detection system for Swedish learner essays.},
	booktitle    = {Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024), March 21, 2024, St. Julian’s, Malta},
	author       = {Szawerna, Maria Irena and Dobnik, Simon and Muñoz Sánchez, Ricardo and Lindström Tiedemann, Therese and Volodina, Elena},
	year         = {2024},
	publisher    = {Association for Computational Linguistics},
	ISBN         = {979-8-89176-085-1},
}

@inProceedings{munozsanchez-etal-2024-jingle-342259,
	title        = { Jingle BERT, Jingle BERT, Frozen All the Way: Freezing Layers to Identify CEFR Levels of Second Language Learners Using BERT},
	abstract     = {In this paper, we investigate the question of how much domain adaptation is needed for the task of automatic essay assessment by freezing layers in BERT models. We test our methodology on three different graded language corpora (English, French and Swedish) and find that partially fine-tuning base models improves performance over fully fine-tuning base models, although the number of layers to freeze differs by language. We also look at the effect of freezing layers on different grades in the corpora and find that different layers are important for different grade levels. Finally, our results represent a new state-of-the-art in automatic essay classification for the three languages under investigation.},
	booktitle    = {Proceedings of the 13th Workshop on Natural Language Processing for Computer Assisted Language Learning (NLP4CALL 2024) },
	author       = {Muñoz Sánchez, Ricardo and Alfter, David and Dobnik, Simon and Szawerna, Maria Irena and Volodina, Elena},
	year         = {2024},
	publisher    = {Linköping Electronic Conference Proceedings},
	ISBN         = {978-91-8075-774-4},
}

@inProceedings{munozsanchez-etal-2024-names-336384,
	title        = {Did the Names I Used within My Essay Affect My Score? Diagnosing Name Biases in Automated Essay Scoring},
	abstract     = {Automated essay scoring (AES) of second-language learner essays is a high-stakes task as it can affect the job and educational opportunities a student may have access to. Thus, it becomes imperative to make sure that the essays are graded based on the students’ language proficiency as opposed to other reasons, such as personal names used in the text of the essay. Moreover, most of the research data for AES tends to contain personal identifiable information. Because of that, pseudonymization becomes an important tool to make sure that this data can be freely shared. Thus, our systems should not grade students based on which given names were used in the text of the essay, both for fairness and for privacy reasons. In this paper we explore how given names affect the CEFR level classification of essays of second language learners of Swedish. We use essays containing just one personal name and substitute it for names from lists of given names from four different ethnic origins, namely Swedish, Finnish, Anglo-American, and Arabic. We find that changing the names within the essays has no apparent effect on the classification task, regardless of whether a feature-based or a transformer-based model is used.},
	booktitle    = {Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024), March 21, 2024, Malta },
	author       = {Muñoz Sánchez, Ricardo and Dobnik, Simon and Szawerna, Maria Irena and Lindström Tiedemann, Therese and Volodina, Elena},
	year         = {2024},
	publisher    = {Association for Computational Linguistics},
	ISBN         = {979-8-89176-085-1},
}

@inProceedings{szawerna-etal-2024-pseudonymization-338089,
	title        = {Pseudonymization Categories across Domain Boundaries},
	abstract     = {Linguistic data, a component critical not only for research in a variety of fields but also for the development of various Natural Language Processing (NLP) applications, can contain personal information. As a result, its accessibility is limited, both from a legal and an ethical standpoint. One of the solutions is the pseudonymization of the data. Key stages of this process include the identification of sensitive elements and the generation of suitable surrogates in a way that the data is still useful for the intended task. Within this paper, we conduct an analysis of tagsets that have previously been utilized in anonymization and pseudonymization. We also investigate what kinds of Personally Identifiable Information (PII) appear in various domains. These reveal that none of the analyzed tagsets account for all of the PII types present cross-domain at the level of detailedness seemingly required for pseudonymization. We advocate for a universal system of tags for categorizing PIIs leading up to their replacement. Such categorization could facilitate the generation of grammatically, semantically, and sociolinguistically appropriate surrogates for the kinds of information that are considered sensitive in a given domain, resulting in a system that would enable dynamic pseudonymization while keeping the texts readable and useful for future research in various fields.},
	booktitle    = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), LREC-COLING, 2024 20-25 May, 2024, Torino, Italia},
	author       = {Szawerna, Maria Irena and Dobnik, Simon and Lindström Tiedemann, Therese and Muñoz Sánchez, Ricardo and Vu, Xuan-Son and Volodina, Elena},
	year         = {2024},
	publisher    = {ELRA and ICCL},
	ISBN         = {978-2-493814-10-4},
}

@inProceedings{munozsanchez-2024-when-341073,
	title        = {When Hieroglyphs Meet Technology: A Linguistic Journey through Ancient Egypt Using Natural Language Processing},
	abstract     = {Knowing our past can help us better understand our future. The explosive development of NLP in these past few decades has allowed us to study ancient languages and cultures in ways that we couldn’t have done in the past. However, not all languages have received the same level of attention. Despite its popularity in pop culture, the languages spoken in Ancient Egypt have been somewhat overlooked in terms of NLP research. In this survey paper we give an overview of how NLP has been used to study different variations of the Ancient Egyptian languages. This not only includes Old, Middle, and Late Egyptian but also Demotic and Coptic. We begin by giving a short introduction to these languages and their writing systems, before talking about the corpora and lexical resources that are available digitally. We then show the different NLP tasks that have been tackled for different variations of Ancient Egyptian, as well as the approaches that have been used. We hope that our work can stoke interest in the study of these languages within the NLP community.},
	booktitle    = {3rd Workshop on Language Technologies for Historical and Ancient Languages, LT4HALA 2024 at LREC-COLING 2024 - Workshop Proceedings, 25 May, 2024 Torino, Italia},
	author       = {Muñoz Sánchez, Ricardo},
	year         = {2024},
	publisher    = { ELRA Language Resources Association},
	ISBN         = {9782493814463},
}

@inProceedings{munozsanchez-etal-2024-harnessing-342122,
	title        = {Harnessing GPT to Study Second Language Learner Essays: Can We Use Perplexity to Determine Linguistic Competence?},
	abstract     = {Generative language models have been used to study a wide variety of phenomena in NLP. This allows us to better understand the linguistic capabilities of those models and to better analyse the texts that we are working with. However, these studies have mainly focused on text generated by L1 speakers of English. In this paper we study whether linguistic competence of L2 learners of Swedish (through their performance on essay tasks) correlates with the perplexity of a decoder-only model (GPT-SW3). We run two sets of experiments, doing both quantitative and qualitative analyses for each of them. In the first one, we analyse the perplexities of the essays and compare them with the CEFR level of the essays, both from an essay-wide level and from a token level. In our second experiment, we compare the perplexity of an L2 learner essay with a normalised version of it. We find that the perplexity of essays tends to be lower for higher CEFR levels and that normalised essays have a lower perplexity than the original versions. Moreover, we find that different factors can lead to spikes in perplexity, not all of them being related to L2 learner language.},
	booktitle    = {Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024), June 20, 2024, Mexico City, Mexico},
	author       = {Muñoz Sánchez, Ricardo and Dobnik, Simon and Volodina, Elena},
	year         = {2024},
	publisher    = {Association for Computational Linguistics},
	address      = { Mexico City, Mexico},
	ISBN         = {979-8-89176-100-1},
}

@inProceedings{munozsanchez-etal-2024-name-339981,
	title        = {Name Biases in Automated Essay Assessment},
	abstract     = {Artificial intelligence is being deployed in high-stakes situations, such as automated grading of second language essays in proficiency assessment. While they can improve the opportunities students have (education, work opportunities, etc.), such systems often display human-like biases. Aldrin (2017) notes that human graders have a slight bias based on names appearing in essay texts. We aim to identify whether the same pattern holds in automated systems. 
In this study we aim to answer the following research questions: 
1) Does changing given names inside a second language learner essay affect the way the text is graded? 
2) How much does this differ between feature-based machine learning and deep learning? 

For this, we use a de-anonymized (i.e. original) version of the Swell-pilot corpus of second language Swedish learner essays (Volodina 2016), which consists of 502 essays annotated with CEFR levels as our source data. 
First, we compile four lists of given names inspired by those of Aldrin (2017): traditional Swedish names; modern Swedish names of Anglo-American origin; Finnish names (due to the close sociocultural links between both countries); and names of Arabic origin (the most prominent group of learners in the corpus). 
Second, we create a diagnostic dataset to identify biases in the classification task. We select SweLL-pilot essays in which a given name appears only once. Then, we generate an essay version for each name on the lists by substituting the name in the original text with one from the list. 
Third, we fine-tune a BERT (Devlin et al. 2019) model on the original SweLL-pilot data to predict the CEFR level of a given essay and compare it to an existing feature-based model (Pilan 2016). 

Finally, we test the two models and compare the equality of opportunity between the different given name groups on the diagnostic dataset. },
	booktitle    = {The 28th International Congress of Onomastic Sciences (ICOS 28),19-23 August, 2024, Helsinki, Finland},
	author       = {Muñoz Sánchez, Ricardo and Dobnik, Simon and Lindström Tiedemann, Therese and Szawerna, Maria Irena and Volodina, Elena},
	year         = {2024},
}

@misc{volodina-etal-2024-proceedings-336386,
	title        = {Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024), March 21, 2024,  Malta},
	author       = {Volodina, Elena and Alfter, David and Dobnik, Simon and Lindström Tiedemann, Therese and Muñoz Sánchez, Ricardo and Szawerna, Maria Irena and Vu, Xuan-Son},
	year         = {2024},
	publisher    = {Association for Computational Linguistics},
	address      = {Stroudsburg, PA },
	ISBN         = {979-8-89176-085-1},
}