相关论文: Generating Synthetic Oracle Datasets to Analyze No…

Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly pronounced when adapting to a specific target domain, such…

Social media platforms like Twitter have increasingly relied on Natural Language Processing NLP techniques to analyze and understand the sentiments expressed in the user generated content. One such state of the art NLP model is…

Reliability of machine learning evaluation -- the consistency of observed evaluation scores across replicated model training runs -- is affected by several sources of nondeterminism which can be regarded as measurement noise. Current…

Natural Language Inference is an important task for Natural Language Understanding. It is concerned with classifying the logical relation between two sentences. In this paper, we propose several text generative neural networks for…

In this paper, we improve semantic segmentation by automatically learning from Flickr images associated with a particular keyword, without relying on any explicit user annotations, thus substantially alleviating the dependence on accurate…

In deep learning (DL) systems, label noise in training datasets often degrades model performance, as models may learn incorrect patterns from mislabeled data. The area of Learning with Noisy Labels (LNL) has introduced methods to…

Recently, online social media has become a primary source for new information and misinformation or rumours. In the absence of an automatic rumour detection system the propagation of rumours has increased manifold leading to serious…

Health mention classification deals with the disease detection in a given text containing disease words. However, non-health and figurative use of disease words adds challenges to the task. Recently, adversarial training acting as a means…

Advanced neural language models (NLMs) are widely used in sequence generation tasks because they are able to produce fluent and meaningful sentences. They can also be used to generate fake reviews, which can then be used to attack online…

Recently, deep learning models have been widely applied in program understanding tasks, and these models achieve state-of-the-art results on many benchmark datasets. A major challenge of deep learning for program understanding is that the…

Owing to the phenomenal success of BERT on various NLP tasks and benchmark datasets, industry practitioners are actively experimenting with fine-tuning BERT to build NLP applications for solving industry use cases. For most datasets that…

Aggressive comments on social media negatively impact human life. Such offensive contents are responsible for depression and suicidal-related activities. Since online social networking is increasing day by day, the hate content is also…

Supervised learning depends on annotated examples, which are taken to be the \emph{ground truth}. But these labels often come from noisy crowdsourcing platforms, like Amazon Mechanical Turk. Practitioners typically collect multiple labels…

Label noise poses a significant challenge in Earth Observation (EO), often degrading the performance and reliability of supervised Machine Learning (ML) models. Yet, given the critical nature of several EO applications, developing robust…

Social media generates an enormous amount of data on a daily basis but it is very challenging to effectively utilize the data without annotating or labeling it according to the target application. We investigate the problem of localized…

Recently, detection of label errors and improvement of label quality in datasets for supervised learning tasks has become an increasingly important goal in both research and industry. The consequences of incorrectly annotated data include…

It is very critical to analyze messages shared over social networks for cyber threat intelligence and cyber-crime prevention. In this study, we propose a method that leverages both domain-specific word embeddings and task-specific features…

Tracking how data is mentioned and used in research papers provides critical insights for improving data discoverability, quality, and production. However, manually identifying and classifying dataset mentions across vast academic…

The problem of detecting bots, automated social media accounts governed by software but disguising as human users, has strong implications. For example, bots have been used to sway political elections by distorting online discourse, to…

Diaspora communities are disproportionately impacted by off-the-radar misinformation and often neglected by mainstream fact-checking efforts, creating a critical need to scale-up efforts of nascent fact-checking initiatives. In this paper…