Sergiu Nisioi

Alexandru-Iulius Jerpelea, Alina Rădoi, Sergiu Nisioi

This paper presents the process of building a neural machine translation system with support for English, Romanian, and Aromanian - an endangered Eastern Romance language. The primary contribution of this research is twofold: (1) the creation of the most extensive Aromanian-Romanian parallel corpus to date, consisting of 79,000 sentence pairs, and (2) the development and comparative analysis of several machine translation models optimized for Aromanian. To accomplish this, we introduce a suite of auxiliary tools, including a language-agnostic sentence embedding model for text mining and automated evaluation, complemented by a diacritics conversion system for different writing standards. This research brings contributions to both computational linguistics and language preservation efforts by establishing essential resources for a historically under-resourced language. All datasets, trained models, and associated tools are public: https://huggingface.co/aronlp and https://arotranslate.com

Jany-Gabriel Ispas, Sergiu Nisioi

This paper describes the system submitted by team \textbf{Archaeology} to SemEval-2026 Task~13 on AI-generated code detection. The shared task consists of three subtasks; we participate in Subtask-A (binary classification: human-written vs.\ AI-generated code) and Subtask-B (11-class attribution of the generating model). Starting from a TF-IDF and Logistic Regression baseline, we fine-tune four pre-trained code models (CodeBERT, GraphCodeBERT, UniXcoder, and CodeT5+) with separate strategies for each subtask. For Subtask-A, we use leave-one-language-out cross-validation, code augmentation, chunked inference with trimmed-mean aggregation, and threshold calibration on a difficult dataset. For Subtask-B, we use sandwich token packing, class-balanced loss, and multi-seed ensembling with test-time augmentation. Our best submissions obtain macro-F1 scores of 0.737 on Subtask-A (6th/81 teams) and 0.422 on Subtask-B (7th/34 teams).

Gabriel Stefan, Sergiu Nisioi

We describe our system for SemEval-2026 Task 6 (CLARITY: Unmasking Political Question Evasions), which classifies English political interview responses by coarse-grained clarity (3-way) and fine-grained evasion strategy (9-way). Since responses frequently exceed the 512-token limit of standard Transformer encoders, we apply an overlapping sliding-window chunking strategy with element-wise Max-Pooling aggregation over chunk representations. A shared RoBERTa-large encoder supplies two task-specific heads trained jointly via a multi-task objective, with inference-time ensembling over 7-fold stratified cross-validation. Our system achieves a Macro-F1 of 0.80 on Subtask 1 and 0.51 on Subtask 2, ranking 11th in both subtasks.

Anastasia Sandu, Teodor Mihailescu, Sergiu Nisioi

This paper describes the work of the UniBuc Archaeology team for CLPsych's 2024 Shared Task, which involved finding evidence within the text supporting the assigned suicide risk level. Two types of evidence were required: highlights (extracting relevant spans within the text) and summaries (aggregating evidence into a synthesis). Our work focuses on evaluating Large Language Models (LLM) as opposed to an alternative method that is much more memory and resource efficient. The first approach employs a good old-fashioned machine learning (GOML) pipeline consisting of a tf-idf vectorizer with a logistic regression classifier, whose representative features are used to extract relevant highlights. The second, more resource intensive, uses an LLM for generating the summaries and is guided by chain-of-thought to provide sequences of text indicating clinical markers.

Ahmad Mustapha Wali, Sergiu Nisioi

Hausa 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 created a large-scale parallel dataset of over 450,000 noisy-clean Hausa sentence pairs by introducing synthetically generated noise, fine-tuned to mimic realistic writing errors. Moreover, we adapted several multilingual and African language-focused models, including M2M100, AfriTEVA, mBART, and Opus-MT variants for this correction task using SentencePiece tokenization. Our experimental results demonstrate significant increases in F1, BLEU and METEOR scores, as well as reductions in Character Error Rate (CER) and Word Error Rate (WER). This research provides a robust methodology, a publicly available dataset, and effective models to improve Hausa text quality, thereby advancing NLP capabilities for the language and offering transferable insights for other low-resource languages.

Steven Bedrick, A. Seza Doğruöz, Sergiu Nisioi

Synthetic 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.

Anca Bucur, Sergiu Nisioi

In this paper we present a data visualization method together with its potential usefulness in digital humanities and philosophy of language. We compile a multilingual parallel corpus from different versions of Wittgenstein's Tractatus Logico-Philosophicus, including the original in German and translations into English, Spanish, French, and Russian. Using this corpus, we compute a similarity measure between propositions and render a visual network of relations for different languages.

Ella Rabinovich, Sergiu Nisioi, Noam Ordan et al.

We 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) non-native 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.