PiCkLe at SemEval-2022 Task 4: Boosting Pre-trained Language Models with Task Specific Metadata and Cost Sensitive Learning

2022-07-01 · SemEval (NAACL) 2022 7 · Manan Suri

This paper describes our system for Task 4 of SemEval 2022: Patronizing and Condescending Language Detection. Patronizing and Condescending Language (PCL) refers to language used with respect to vulnerable communities that portrays them in a pitiful way and is reflective of a sense of superiority. Task 4 involved binary classification (Subtask 1) and multi-label classification (Subtask 2) of Patronizing and Condescending Language (PCL). For our system, we experimented with fine-tuning different transformer-based pre-trained models including BERT, DistilBERT, RoBERTa and ALBERT. Further, we have used token separated metadata in order to improve our model by helping it contextualize different communities with respect to PCL. We faced the challenge of class imbalance, which we solved by experimenting with different class weighting schemes. Our models were effective in both subtasks, with the best performance coming out of models with Effective Number of Samples (ENS) class weighting and token separated metadata in both subtasks. For subtask 1 and subtask 2, our best models were finetuned BERT and RoBERTa models respectively.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Binary Classification Multi-Label Classification MUlTI-LABEL-ClASSIFICATION

PickleTeam! at SemEval-2018 Task 2: English and Spanish Emoji Prediction from Tweets

2018-06-01 · SEMEVAL 2018 6 · Daphne Groot, R{\'e}mon Kruizinga, Hennie Veldthuis, Simon de Wit 외

We present a system for emoji prediction on English and Spanish tweets, prepared for the SemEval-2018 task on Multilingual Emoji Prediction. We compared the performance of an SVM, LSTM and an ensemble of these two. We fo…

Medical Diagnosis Prediction Task 2

PickleBall: Secure Deserialization of Pickle-based Machine Learning Models (Extended Report)

2025-08-21 · Andreas D. Kellas, Neophytos Christou, Wenxin Jiang, Penghui Li 외 arxiv

Machine learning model repositories such as the Hugging Face Model Hub facilitate model exchanges. However, bad actors can deliver malware through compromised models. Existing defenses such as safer model formats, restri…

Nova-Wang at SemEval-2020 Task 12: OffensEmblert: An Ensemble ofOffensive Language Classifiers

2020-12-01 · SEMEVAL 2020 · Susan Wang, Zita Marinho

This paper presents our contribution to the Offensive Language Classification Task (English SubTask A) of Semeval 2020. We propose different Bert models trained on several offensive language classification and profanity …

Classification regression

SafePickle: Robust and Generic ML Detection of Malicious Pickle-based ML Models

2026-02-23 · Hillel Ohayon, Daniel Gilkarov, Ran Dubin arxiv

Model repositories such as Hugging Face increasingly distribute machine learning artifacts serialized with Python's pickle format, exposing users to remote code execution (RCE) risks during model loading. Recent defenses…

Randomized Physics-Informed Machine Learning for Uncertainty Quantification in High-Dimensional Inverse Problems

2023-12-11 · Yifei Zong, David Barajas-Solano, Alexandre M. Tartakovsky

We propose a physics-informed machine learning method for uncertainty quantification in high-dimensional inverse problems. In this method, the states and parameters of partial differential equations (PDEs) are approximat…

Physics-informed machine learning Uncertainty Quantification