Demo Data from VLDB 2026 / reviewers in the wild / expert
Sergiu Nisioi
dblp:127/0120
· DBLP profile ↗
18ranked-venue papers
4as first author
10since 2021 · last 2026
0000-0003-2247-4488ORCID · corroborated
Domains — the database's venue-derived domains; a paper can count in several
Artificial intelligence and machine learning · 16 · 4 first-author · 8 since 2021Databases, data management, data science and information retrieval · 2 · 1 first-author · 1 since 2021Graphics, computer vision, multimedia, augmented reality and games · 2 · 2 since 2021Human-computer interaction and ubiquitous computing · 2 · 2 since 2021
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
3 papers |
Language models and text generation · 69% Information extraction and text analysis · 20% Machine translation · 11% | |
| Databases, data mining, and information retrieval
1 paper |
Information retrieval · 50% Recommender systems · 50% |
Topics — the 7 heaviest of 9, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Natural language and speech › Language models and text generation
text correction |
1.0 | 1 | 2026 | Automatic Correction of Writing Anomalies in Hausa Texts · ACL (1) 2026 |
Natural language and speech › Language models and text generation › text generation › text simplification
lexical simplification |
0.9 | 1 | 2025 | RALS: Resources and Baselines for Romanian Automatic Lexical Simplification · EMNLP 2025 |
Natural language and speech › Language models and text generation › text generation
text simplification |
0.9 | 1 | 2025 | RALS: Resources and Baselines for Romanian Automatic Lexical Simplification · EMNLP 2025 |
Natural language and speech › Language models and text generation
low-resource language processing |
0.3 | 1 | 2026 | Automatic Correction of Writing Anomalies in Hausa Texts · ACL (1) 2026 |
Recommender systems › personalized ranking
pairwise ranking |
0.3 | 1 | 2025 | RALS: Resources and Baselines for Romanian Automatic Lexical Simplification · EMNLP 2025 |
Information retrieval
ranking |
0.3 | 1 | 2025 | RALS: Resources and Baselines for Romanian Automatic Lexical Simplification · EMNLP 2025 |
Natural language and speech › Machine translation
translationese |
0.2 | 1 | 2016 | On the Similarities Between Native, Non-native and Translated Texts · ACL (1) 2016 |
Methods — techniques the papers use, named apart from their topics
pairwise ranking approximation · 1.7synthetic noise generation · 1.0fine-tuning · 1.0
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2026 | Automatic Correction of Writing Anomalies in Hausa TextsabstractHausa texts are often characterized by writing anomalies such as incorrect character substitutions and spacing errors, which sometimes hinder natural language processing (NLP) applications.This paper presents an approach to automatically correct the anomalies by finetuning transformer-based models.Using a corpus gathered from several public sources, we create a large-scale parallel dataset of over 400,000 noisy-clean Hausa sentence pairs by introducing synthetically generated noise to mimic realistic writing errors.Moreover, we finetune several multilingual and African language models, including M2M100, AfriTeVA, NCAIR1/N-ATLaS, UBC-NLP/cheetah-base, and other variants of BART and T5 for this correction task.Our experimental results demonstrate that models such as M2M100 achieve state-of-the-art results despite their smaller size and distinct pretraining, and that correcting errors can have a significant impact in improving downstream tasks such as text classification, machine translation, question answering, and LLM prompting in general.This research provides a methodology, a publicly available dataset, and a comparison of models to improve Hausa text quality, thereby advancing NLP capabilities for the language and offering transferable insights for other low-resource languages. Ahmad Mustapha Wali, Sergiu Nisioi |
ACL (1) | 2 |
| 2026 | Analyzing the Relationship Between Reading Times and Lexical Complexity Prediction in RomanianabstractIn this work we investigate the relationship between explicit lexical complexity judgments and implicit reading behavior in Romanian. Using the Romanian Lexical Complexity Prediction (RoLCP) dataset and newly collected eye-tracking recordings following the MultiplEYE framework, we provide an initial analysis on how perceived word difficulty relates to total reading time (TRT). Our results show that surface-level features, particularly word length and frequency, are strong predictors of reading effort, while human complexity ratings have an asymmetric relationship to the reading times. Overall, our findings highlight the complementary nature of explicit annotations and implicit behavioral measures, and provide a comparative analysis of the performance of predictors from LLM layer-wise linear probes. Oleksandra Kuvshynova, Mircea Mihai Marin, Sergiu Nisioi |
ETRA | 3 |
| 2026 | A Typology of Synthetic Datasets for Dialogue Processing in Clinical ContextsabstractSynthetic data sets are used across linguistic domains and NLP tasks, particularly in scenarios where authentic data is limited (or even non-existent). One such domain is that of clinical (healthcare) contexts, where there exist significant and long-standing challenges (e.g., privacy, anonymization, and data governance) which have led to the development of an increasing number of synthetic datasets. One increasingly important category of clinical dataset is that of clinical dialogues which are especially sensitive and difficult to collect, and as such are commonly synthesized. While such synthetic datasets have been shown to be sufficient in some situations, little theory exists to inform how they may be best used and generalized to new applications. In this paper, we provide an overview of how synthetic datasets are created, evaluated and being used for dialogue related tasks in the medical domain. Additionally, we propose a novel typology for use in classifying types and degrees of data synthesis, to facilitate comparison and evaluation. Steven Bedrick, A. Seza Dogruöz, Sergiu Nisioi |
LREC | 3 |
| 2026 | The MultiplEYE Text Corpus: Towards a Diverse and Ever-Expanding Multilingual Text Corpus
Ramune Kaspere, Anna Bondar, Sergiu Nisioi, Maja Stegenwallner-Schütz, Hanne B. Søndergaard Knudsen, Ana Matic Skoric, Eva Pavlinusic Vilus, Dorota Klimek-Jankowska, Chiara Tschirner, Not Battesta Soliva, Deborah N. Jakobi, Cui Ding, Dima Abu Romi, Cengiz Acartürk, Matilda Agdler, Anton Marius Alexandru, Mohd Faizan Ansari, Annalisa Arcidiacono, Elizabete Ausma Velta Barisa, Ana Bautista, Lisa Beinborn, Yevgeni Berzak, Nedeljka Bjelanovic, Anna Isabelle Bothmann, Jan Brasser, Caterina Cacioli, Anila Çepani, Ilze Ceple, Adelina Çerpja, Dalí Chirino, Jan Chromý, Alessandro Corona Mendozza, Iria de-Dios-Flores, Nazik Dinçtopal Deniz, Ana Dosen, Kristian Elersic, Inmaculada Fajardo, Zigmunds Freibergs, Angelina Ganebnaya, Jessica Gomes, Annjo Klungervik Greenall, Alba Haveriku, Anamaria Hodivoianu, Yu-Yin Hsu, Amanda Isaksen, Andreia Janeiro, Kristine M. Jensen de López, Aleksandar Jevremovic, Vojislav Jovanovic, Hanna Kedzierska, Nik Kharlamov, Sara Kosutar, Nelda Kote, Vanja Kovic, Izabela Krejtz, Thyra Krosness, Oleksandra Kuvshynova, Eilam Lavy, Ella Lion, Marta Lockiewicz, Kaidi Lõo, Paula Luegi, Mircea Mihai Marin, Clara Martin, Svitlana Matvieieva, Diane C. Mézière, Xavier Mínguez-López, Valeriia Modina, Jurgita Motiejuniene, Marie-Luise Müller, Tolgonai Nasipbek kyzy, Jamal Abdul Nasir, Johanne Sofie Krog Nedergård, Aysegül Özkan, Patrizia Paggio, Marijan Palmovic, Maria Christina Panagiotopoulou, Alberto Parola, Helena Pérez, Klaudia Petersen, Anja Podlesek, Eva Pospísilová, Marta Praulina, Mikulás Preininger, Loredana Punga, Diego Rossini, Spela Rot, Habib Sani Yahaya, Irina A. Sekerina, Anne Gabija Skadina, Jordi Solé i Casals, Lonneke van der Plas, Saara M. Varjopuro, Spyridoula Varlokosta, João Veríssimo, Oskari Juhapekka Virtanen, Nemanja Vracar, Mila Dimitrova-Vulchanova, Ahmad Mustapha Wali, Peizheng Wu, Nilgün Yücel, Stefan Frank, Nora Hollenstein, Lena A. Jäger, Somayeh Bakhtiari |
LREC | 3 |
| 2026 | Mitigating Gender Bias in English to Romanian Machine TranslationabstractMachine translation (MT) systems often fail to correctly translate gender, especially when converting from a gender-neutral language like English to a gendered target language such as Romanian. This bias results in translations that default to masculine forms or reinforce gender stereotypes. We propose a hybrid pipeline to mitigate this issue by combining large language model (LLM)-based gender classification with neural machine translation (NMT). Our system uses a fine-tuned LLM to detect the intended gender of target words in English sentences and insert inline gender hint tags. These tagged sentences are then passed to a Transformer model fine-tuned to generate morphologically correct Romanian translations. To support this, we introduce three novel datasets for gender disambiguation and translation. Our approach improves gender accuracy on the WinoMT and WinoGender benchmarks by over 40% points compared to a baseline MT system. This is the first method to explicitly address and evaluate gender bias in English–Romanian MT using both LLM inference and tag-aware translation. Ioana Grigore, Sergiu Nisioi |
NLDB | 2 |
| 2025 | Dialectal and Low Resource Machine Translation for AromanianabstractWe present a neural machine translation system that can translate between Romanian, English, and Aromanian (an endangered Eastern Romance language); the first of its kind. BLEU scores range from 17 to 32 depending on the direction and genre of the text. Alongside, we release the biggest known Aromanian-Romanian bilingual corpus, consisting of 80k cleaned sentence pairs. Additional tools such as an agnostic sentence embedder (used for both text mining and automatic evaluation) and a diacritics converter are also presented. Lastly, we describe the online deployment of our quantized model, considering a CPU-driven limited resource scenario. Alexandru-Iulius Jerpelea, Alina-Stefania Radoi, Sergiu Nisioi |
COLING | 3 |
| 2025 | RALS: Resources and Baselines for Romanian Automatic Lexical SimplificationabstractWe introduce the first dataset that jointly covers both lexical complexity prediction (LCP) annotations and lexical simplification (LS) for Romanian, along with a comparison of lexical simplification approaches.We propose a methodology for ordering simplification suggestions using a pairwise ranking approximation method, arranging candidates from simple to complex based on a separate set of human judgments.In addition, we provide human lexical complexity annotations for 3,921 word samples in context.Finally, we explore several novel pipelines for complexity prediction and simplification and present the first text simplification system for Romanian. Fabian Anghel, Cristea Petru-Theodor, Claudiu Creanga, Sergiu Nisioi |
EMNLP | 4 |
| 2025 | The More the Merrier: Boost Your Dataset Visibility and Discover Eye-Tracking Datasets with pymovements
Daniel Krakowczyk, David R. Reich, Andreas Säuberli, Iza Skrjanec, Isabelle Caroline Rose Cretton, Deborah N. Jakobi, Sergiu Nisioi, Paul Prasse, Lena A. Jäger |
ETRA | 7 |
| 2024 | A Multilingual Parallel Corpus for AromanianabstractWe 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. Iulia Petrariu, Sergiu Nisioi |
LREC/COLING | 2 |
| 2022 | Identifying Draft Bills Impacting Existing Legislation: a Case Study on RomanianabstractIn our paper, we present a novel corpus of historical legal documents on the Romanian public procurement legislation and an annotated subset of draft bills that have been screened by legal experts and identified as impacting past public procurement legislation. Using the manual annotations provided by the experts, we attempt to automatically identify future draft bills that have the potential to impact existing policies on public procurement. Corina Ceausu, Sergiu Nisioi |
LREC | 2 |
| 2020 | CoCo: A Tool for Automatically Assessing Conceptual Complexity of TextsabstractTraditional text complexity assessment usually takes into account only syntactic and lexical text complexity. The task of automatic assessment of conceptual text complexity, important for maintaining reader’s interest and text adaptation for struggling readers, has only been proposed recently. In this paper, we present CoCo - a tool for automatic assessment of conceptual text complexity, based on using the current state-of-the-art unsupervised approach. We make the code and API freely available for research purposes, and describe the code and the possibility for its personalization and adaptation in details. We compare the current implementation with the state of the art, discussing the influence of the choice of entity linker on the performances of the tool. Finally, we present results obtained on two widely used text simplification corpora, discussing the full potential of the tool. Sanja Stajner, Sergiu Nisioi, Ioana Hulpus |
LREC | 2 |
| 2018 | A Detailed Evaluation of Neural Sequence-to-Sequence Models for In-domain and Cross-domain Text Simplification
Sanja Stajner, Sergiu Nisioi |
LREC | 2 |
| 2016 | On the Similarities Between Native, Non-native and Translated TextsabstractWe present a computational analysis of three language varieties: native, advanced non-native, and translation. Our goal is to investigate the similarities and differences between non-native language productions and translations, contrasting both with native language. Using a collection of computational methods we establish three main results: (1) the three types of texts are easily distinguishable; (2) nonnative language and translations are closer to each other than each of them is to native language; and (3) some of these characteristics depend on the source or native language, while others do not, reflecting, perhaps, unified principles that similarly affect translations and non-native language. Ella Rabinovich, Sergiu Nisioi, Noam Ordan, Shuly Wintner |
ACL (1) | 2 |
| 2016 | Comparing Speech and Text Classification on ICNALE
Sergiu Nisioi |
LREC | 1 |
| 2016 | A Corpus of Native, Non-native and Translated Texts
Sergiu Nisioi, Ella Rabinovich, Liviu P. Dinu, Shuly Wintner |
LREC | 1 |
| 2016 | Using Word Embeddings to Translate Named Entities
Octavia-Maria Sulea, Sergiu Nisioi, Liviu P. Dinu |
LREC | 2 |
| 2015 | Feature Analysis for Native Language Identification
Sergiu Nisioi |
CICLing (1) | 1 |
| 2015 | Unsupervised Classification of Translated Texts
Sergiu Nisioi |
NLDB | 1 |