相关论文: Is Your Model Sensitive? SPeDaC: A New Benchmark f…

The detection of sexism in online content remains an open problem, as harmful language disproportionately affects women and marginalized groups. While automated systems for sexism detection have been developed, they still face two key…

Machine learning models can perpetuate unintended biases from unfair and imbalanced datasets. Evaluating and debiasing these datasets and models is especially hard in text datasets where sensitive attributes such as race, gender, and sexual…

Semantic textual similarity is one of the open research challenges in the field of Natural Language Processing. Extensive research has been carried out in this field and near-perfect results are achieved by recent transformer-based models…

Objective: To detect and classify features of stigmatizing and biased language in intensive care electronic health records (EHRs) using natural language processing techniques. Materials and Methods: We first created a lexicon and regular…

Software logs are messages recorded during the execution of a software system that provide crucial run-time information about events and activities. Although software logs have a critical role in software maintenance and operation tasks,…

A powerful approach to detecting erroneous data is to check which potentially dirty data records are incompatible with a user's domain knowledge. Previous approaches allow the user to specify domain knowledge in the form of logical…

The detection of sensitive content in large datasets is crucial for ensuring that shared and analysed data is free from harmful material. However, current moderation tools, such as external APIs, suffer from limitations in customisation,…

Suicidal thoughts and behaviors are increasingly recognized as a critical societal concern, highlighting the urgent need for effective tools to enable early detection of suicidal risk. In this work, we develop robust machine learning models…

High-quality labeled datasets are crucial for training and evaluating foundation models in software engineering, but creating them is often prohibitively expensive and labor-intensive. We introduce SPICE, a scalable, automated pipeline for…

Sentiment classification is a quickly advancing field of study with applications in almost any field. While various models and datasets have shown high accuracy inthe task of binary classification, the task of fine-grained sentiment…

By design, word embeddings are unable to model the dynamic nature of words' semantics, i.e., the property of words to correspond to potentially different meanings. To address this limitation, dozens of specialized meaning representation…

The emergence of open data portals necessitates more attention to protecting sensitive data before datasets get published and exchanged. To do so effectively, we observe the need to refine and broaden our definitions of sensitive data, and…

The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such problem. Recent works show that self-training is…

We introduce a new framework, dubbed Cerberus, for attribute-based person re-identification (reID). Our approach leverages person attribute labels to learn local and global person representations that encode specific traits, such as gender…

Semi-Supervised Domain Adaptation (SSDA) is a recently emerging research topic that extends from the widely-investigated Unsupervised Domain Adaptation (UDA) by further having a few target samples labeled, i.e., the model is trained with…

We present SParC, a dataset for cross-domainSemanticParsing inContext that consists of 4,298 coherent question sequences (12k+ individual questions annotated with SQL queries). It is obtained from controlled user interactions with 200…

Data selection seeks to identify a compact yet informative subset from large-scale training corpora, balancing sample quality against collection diversity. We formulate this problem as a Weighted Independent Set (WIS) on a similarity graph,…

The task of text and sentence classification is associated with the need for large amounts of labelled training data. The acquisition of high volumes of labelled datasets can be expensive or unfeasible, especially for highly-specialised…

Learning semantic segmentation models requires a huge amount of pixel-wise labeling. However, labeled data may only be available abundantly in a domain different from the desired target domain, which only has minimal or no annotations. In…

The paper investigates the feasibility of confidence estimation for neural machine translation models operating at the high end of the performance spectrum. As a side product of the data annotation process necessary for building such models…