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

As open-ended human-chatbot interaction becomes commonplace, sensitive content detection gains importance. In this work, we propose a two stage semi-supervised approach to bootstrap large-scale data for automatic sensitive language…

Effective item identifiers (IDs) are an important component for recommender systems (RecSys) in practice, and are commonly adopted in many use cases such as retrieval and ranking. IDs can encode collaborative filtering signals within…

Domain adaptation assumes that samples from source and target domains are freely accessible during a training phase. However, such an assumption is rarely plausible in the real-world and possibly causes data-privacy issues, especially when…

Domain adaptation (DA) paves the way for label annotation and dataset bias issues by the knowledge transfer from a label-rich source domain to a related but unlabeled target domain. A mainstream of DA methods is to align the feature…

In practical machine learning applications, it is often challenging to assign accurate labels to data, and increasing the number of labeled instances is often limited. In such cases, Weakly Supervised Learning (WSL), which enables training…

Sociodemographic biases are a common problem for natural language processing, affecting the fairness and integrity of its applications. Within sentiment analysis, these biases may undermine sentiment predictions for texts that mention…

We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…

Categorical speech emotion recognition is typically performed as a sequence-to-label problem, i.e., to determine the discrete emotion label of the input utterance as a whole. One of the main challenges in practice is that most of the…

In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unannotated target datasets that differ in their underlying data…

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…

In many critical applications, sensitive data is inherently distributed and cannot be centralized due to privacy concerns. A wide range of federated learning approaches have been proposed to train models locally at each client without…

This paper investigates the semantic robustness of attention-based classifiers for design pattern detection, particularly focusing on their reliance on structural and behavioral semantics. We reproduce the DPDAtt, an attention-based design…

Personality refers to individual differences in behavior, thinking, and feeling. With the growing availability of digital footprints, especially from social media, automated methods for personality assessment have become increasingly…

User language data can contain highly sensitive personal content. As such, it is imperative to offer users a strong and interpretable privacy guarantee when learning from their data. In this work, we propose SentDP: pure local differential…

Presently, self-training stands as a prevailing approach in cross-domain semantic segmentation, enhancing model efficacy by training with pixels assigned with reliable pseudo-labels. However, we find two critical limitations in this…

Document categorization, which aims to assign a topic label to each document, plays a fundamental role in a wide variety of applications. Despite the success of existing studies in conventional supervised document classification, they are…

Customers' reviews and comments are important for businesses to understand users' sentiment about the products and services. However, this data needs to be analyzed to assess the sentiment associated with topics/aspects to provide efficient…

Suicide is a prominent issue in society. Unfortunately, many people at risk for suicide do not receive the support required. Barriers to people receiving support include social stigma and lack of access to mental health care. With the…

Semi-supervised domain adaptation (SSDA) adapts a learner to a new domain by effectively utilizing source domain data and a few labeled target samples. It is a practical yet under-investigated research topic. In this paper, we analyze the…

Much effort has been devoted to understanding the decisions of deep neural networks in recent years. A number of model-aware saliency methods were proposed to explain individual classification decisions by creating saliency maps. However,…