SG-UniBuc-NLP at SemEval-2026 Task 6: Multi-Head RoBERTa with Chunking for Long-Context Evasion Detection

2026-04-29 · Gabriel Stefan, Sergiu Nisioi arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.26375

Code (0)

등록된 구현이 없습니다.

Mao-Zedong At SemEval-2023 Task 4: Label Represention Multi-Head Attention Model With Contrastive Learning-Enhanced Nearest Neighbor Mechanism For Multi-Label Text Classification

2023-07-11 · Che Zhang, Ping'an Liu, Zhenyang Xiao, Haojun Fei

The study of human values is essential in both practical and theoretical domains. With the development of computational linguistics, the creation of large-scale datasets has made it possible to automatically recognize hu…

Contrastive Learning Multi Label Text Classification Multi-Label Text Classification text-classification+1

Few-shot text-based emotion detection

2025-07-08 · Teodor-George Marchitan, Claudiu Creanga, Liviu P. Dinu arxiv

This paper describes the approach of the Unibuc - NLP team in tackling the SemEval 2025 Workshop, Task 11: Bridging the Gap in Text-Based Emotion Detection. We mainly focused on experiments using large language models (G…

ALB at SemEval-2018 Task 10: A System for Capturing Discriminative Attributes

2018-06-01 · SEMEVAL 2018 6 · Bogdan Dumitru, Alina Maria Ciobanu, Liviu P. Dinu

Semantic difference detection attempts to capture whether a word is a discriminative attribute between two other words. For example, the discriminative feature red characterizes the first word from the (apple, banana) pa…

Attribute Dependency Parsing Machine Translation Semantic Parsing+1

LT3 at SemEval-2020 Task 7: Comparing Feature-Based and Transformer-Based Approaches to Detect Funny Headlines

2020-12-01 · SEMEVAL 2020 · Bram Vanroy, Sofie Labat, Olha Kaminska, Els Lefever 외

This paper presents two different systems for the SemEval shared task 7 on Assessing Humor in Edited News Headlines, sub-task 1, where the aim was to estimate the intensity of humor generated in edited headlines. Our fir…

Language Modeling Language Modelling named-entity-recognition Named Entity Recognition+2

Transformer and Hybrid Deep Learning Based Models for Machine-Generated Text Detection

2024-05-28 · Teodor-George Marchitan, Claudiu Creanga, Liviu P. Dinu

This paper describes the approach of the UniBuc - NLP team in tackling the SemEval 2024 Task 8: Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection. We explored transformer-based and …

Text Detection