diff --git a/content/pubs.bib b/content/pubs.bib index 08f3e6b..52e0c41 100644 --- a/content/pubs.bib +++ b/content/pubs.bib @@ -1,4 +1,145 @@ + + +@inproceedings{florescu-etal-2024-upon, + title = "Once Upon a Replication: It is Humans{'} Turn to Evaluate {AI}{'}s Understanding of Children{'}s Stories for {QA} Generation", + author = "Florescu, Andra-Maria and + Micluta-Campeanu, Marius and + Dinu, Liviu P.", + editor = "Balloccu, Simone and + Belz, Anya and + Huidrom, Rudali and + Reiter, Ehud and + Sedoc, Joao and + Thomson, Craig", + booktitle = "Proceedings of the Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024", + month = may, + year = "2024", + address = "Torino, Italia", + publisher = "ELRA and ICCL", + url = "https://aclanthology.org/2024.humeval-1.10", + pages = "106--113", + abstract = "The following paper presents the outcomes of a collaborative experiment on human evaluation from the ReproNLP 2024 shared task, track B, part of the ReproHum project. For this paper, we evaluated a QAG (question-answer generation) system centered on English children{'}s storybooks that was presented in a previous research, by using human evaluators for the study. The system generated relevant QA (Question-Answer) pairs based on a dataset with storybooks for early education (kindergarten up to middle school) called FairytaleQA. In the framework of the ReproHum project, we first outline the previous paper and the reproduction strategy that has been decided upon. The complete setup of the first human evaluation is then described, along with the modifications required to replicate it. We also add other relevant related works on this subject. In conclusion, we juxtapose the replication outcomes with those documented in the cited publication. Additionally, we explore the general features of this endeavor as well as its shortcomings.", +} + + +@article{creanga2024automated, + title={Automated Text Identification Using CNN and Training Dynamics}, + author={Creanga, Claudiu and Dinu, Liviu Petrisor}, + journal={arXiv preprint arXiv:2405.11212}, + year={2024} +} + + +@article{marchitan2024transformer, + title={Transformer and Hybrid Deep Learning Based Models for Machine-Generated Text Detection}, + author={Marchitan, Teodor-George and Creanga, Claudiu and Dinu, Liviu P}, + journal={arXiv preprint arXiv:2405.17964}, + year={2024} +} + + +@inproceedings{dinu-etal-2024-pater-incertus, + title = "Pater Incertus? There Is a Solution: Automatic Discrimination between Cognates and Borrowings for {R}omance Languages", + author = "Dinu, Liviu P. and + Uban, Ana Sabina and + Iordache, Ioan-Bogdan and + Cristea, Alina Maria and + Georgescu, Simona and + Zoicas, Laurentiu", + 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.1108", + pages = "12657--12667", + abstract = "Identifying the type of relationship between words (cognates, borrowings, inherited) provides a deeper insight into the history of a language and allows for a better characterization of language relatedness. In this paper, we propose a computational approach for discriminating between cognates and borrowings, one of the most difficult tasks in historical linguistics. We compare the discriminative power of graphic and phonetic features and we analyze the underlying linguistic factors that prove relevant in the classification task. We perform experiments for pairs of languages in the Romance language family (French, Italian, Spanish, Portuguese, and Romanian), based on a comprehensive database of Romance cognates and borrowings. To our knowledge, this is one of the first attempts of this kind and the most comprehensive in terms of covered languages.", +} + + +@inproceedings{petru, +title={{Archaeology at MLSP 2024: Machine Translation for Lexical Complexity Prediction and Lexical Simplification}}, +author={Cristea Petru-Theodor and Sergiu Nisioi}, +booktitle={Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA)}, +year={2024} +} + +@inproceedings{arhitectura, + author={{Andreea Robu-Movila and Sabin-Andrei Tenea and Alexandru Berceanu and Sergiu Nisioi and Constantin Pistol and Grigore Burloiu}}, + title={{Neuroarchitecture: from effective computing to affective computing}}, + booktitle={{DigitalFUTURES CDRF}}, + year={2024} +} + + +@inproceedings{entityLinking2024, + author={Raluca Tudor and Sergiu Nisioi}, + title={{Building an Entity Linking Dataset for Romanian}}, + booktitle={Recent Advances in Digital Humanities}, + year={2024} +} + + +@inproceedings{sandu2024cheap, + title={Cheap Ways of Extracting Clinical Markers from Texts}, + author={Sandu, Anastasia and Mihailescu, Teodor and Nisioi, Sergiu}, + booktitle={Proceedings of the 9th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2024)}, + pages={256--263}, + year={2024} +} + + +@inproceedings{petrariu-nisioi-2024-multilingual-parallel, + title = "A Multilingual Parallel Corpus for {A}romanian", + author = "Petrariu, Iulia and + Nisioi, Sergiu", + 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.75", + pages = "832--838", + abstract = "We report the creation of the first high-quality corpus of Aromanian - an endangered Romance language spoken in the Balkans - and the equivalent sentence-aligned translations into Romanian, English, and French. The corpus is released publicly using several orthographic standards and consists in short stories collected in the {`}70s in Romania. Additionally, we provide an corpus-based analysis of Aromanian linguistic particularities and the overall demographic and political context which impacts the contemporary development of the language.", +} + + +@inproceedings{mihalcea-nisioi-2023-clark, + title = "{C}lark {K}ent at {S}em{E}val-2023 Task 5: {SVM}s, Transformers, and Pixels for Clickbait Spoiling", + author = "Mihalcea, Dragos-stefan and + Nisioi, Sergiu", + editor = {Ojha, Atul Kr. and + Do{\u{g}}ru{\"o}z, A. Seza and + Da San Martino, Giovanni and + Tayyar Madabushi, Harish and + Kumar, Ritesh and + Sartori, Elisa}, + booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)", + month = jul, + year = "2023", + address = "Toronto, Canada", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2023.semeval-1.167", + doi = "10.18653/v1/2023.semeval-1.167", + pages = "1204--1212", + abstract = "In this paper we present an analysis of our approaches for the 2023 SemEval-2023 Clickbait Challenge. We only participated in the sub-task aiming at identifying different clikcbait spoiling types comparing several machine learning and deep learning approaches. Our analysis confirms previous results on this task and show that automatic methods are able to reach approximately 70{\textbackslash}{\%} accuracy at predicting what type of additional content is needed to mitigate sensationalistic posts on social media. Furthermore, we provide a qualitative analysis of the results, showing that the models may do better in practice than the metric indicates since the evaluate does not depend only on the predictor, but also on the typology we choose to define clickbait spoiling.", +} + + + @techreport{nlpunibuc-2022-mt-mental-health, author = "Iordachescu Anca-Mihaela and Stan Flavius-Stefan", title = "An Evaluation of Machine Translation for Multilingual Mental Health Detection",