Related papers: SimANS: Simple Ambiguous Negatives Sampling for De…

Neural Encoders are frequently used in the NLP domain to perform dense retrieval tasks, for instance, to generate the candidate documents for a given query in question-answering tasks. However, sparse annotation and label noise in the…

Implicit feedback (e.g., clicks, dwell times, etc.) is an abundant source of data in human-interactive systems. While implicit feedback has many advantages (e.g., it is inexpensive to collect, user centric, and timely), its inherent biases…

Importance sampling, which involves sampling from a probability density function (PDF) proportional to the product of an importance weight function and a base PDF, is a powerful technique with applications in variance reduction, biased or…

When deploying machine learning models in high-stakes robotics applications, the ability to detect unsafe situations is crucial. Early warning systems can provide alerts when an unsafe situation is imminent (in the absence of corrective…

Falsely annotated samples, also known as noisy labels, can significantly harm the performance of deep learning models. Two main approaches for learning with noisy labels are global noise estimation and data filtering. Global noise…

Word2Vec is the most popular model for word representation and has been widely investigated in literature. However, its noise distribution for negative sampling is decided by empirical trials and the optimality has always been ignored. We…

Learning with noisy labels has gained increasing attention because the inevitable imperfect labels in real-world scenarios can substantially hurt the deep model performance. Recent studies tend to regard low-loss samples as clean ones and…

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…

In real-world scenarios with naturally occurring datasets, reference summaries are noisy and may contain information that cannot be inferred from the source text. On large news corpora, removing low quality samples has been shown to reduce…

This paper proposes an efficient example selection method for example-based word sense disambiguation systems. To construct a practical size database, a considerable overhead for manual sense disambiguation is required. Our method is…

We define a notion of information that an individual sample provides to the training of a neural network, and we specialize it to measure both how much a sample informs the final weights and how much it informs the function computed by the…

In machine learning models, the estimation of errors is often complex due to distribution bias, particularly in spatial data such as those found in environmental studies. We introduce an approach based on the ideas of importance sampling to…

Dense retrieval models are commonly used in Information Retrieval (IR) applications, such as Retrieval-Augmented Generation (RAG). Since they often serve as the first step in these systems, their robustness is critical to avoid downstream…

In learning with noisy labels, the sample selection approach is very popular, which regards small-loss data as correctly labeled during training. However, losses are generated on-the-fly based on the model being trained with noisy labels,…

Online misinformation has been considered as one of the top global risks as it may cause serious consequences such as economic damages and public panic. The misinformation prevention problem aims at generating a positive cascade with…

Curating an informative and representative dataset is essential for enhancing the performance of 2D object detectors. We present a novel active learning sampling strategy that addresses both the informativeness and diversity of the…

In supervised learning, we often face with ambiguous (A) samples that are difficult to label even by domain experts. In this paper, we consider a binary classification problem in the presence of such A samples. This problem is substantially…

Retrieving information from an online search engine, is the first and most important step in many data mining tasks. Most of the search engines currently available on the web, including all social media platforms, are black-boxes (a.k.a…

Optimizing the phrasing of argumentative text is crucial in higher education and professional development. However, assessing whether and how the different claims in a text should be revised is a hard task, especially for novice writers. In…

Alleviating the delayed feedback problem is of crucial importance for the conversion rate(CVR) prediction in online advertising. Previous delayed feedback modeling methods using an observation window to balance the trade-off between waiting…