Related papers: VIBE: Topic-Driven Temporal Adaptation for Twitter…
The digital town hall of Twitter becomes a preferred medium of communication for individuals and organizations across the globe. Some of them reach audiences of millions, while others struggle to get noticed. Given the impact of social…
The present study proposes a novel method of trend detection and visualization - more specifically, modeling the change in a topic over time. Where current models used for the identification and visualization of trends only convey the…
Notwithstanding recent work which has demonstrated the potential of using Twitter messages for content-specific data mining and analysis, the depth of such analysis is inherently limited by the scarcity of data imposed by the 140 character…
We introduce VIBA, a novel approach for explainable video classification by adapting Information Bottlenecks for Attribution (IBA) to video sequences. While most traditional explainability methods are designed for image models, our IBA…
For unsupervised domain adaptation problems, the strategy of aligning the two domains in latent feature space through adversarial learning has achieved much progress in image classification, but usually fails in semantic segmentation tasks…
Speech models have long been known to overfit individual speakers for many classification tasks. This leads to poor generalization in settings where the speakers are out-of-domain or out-of-distribution, as is common in production…
During the onset of a disaster event, filtering relevant information from the social web data is challenging due to its sparse availability and practical limitations in labeling datasets of an ongoing crisis. In this paper, we hypothesize…
Fake news detection has been a critical task for maintaining the health of the online news ecosystem. However, very few existing works consider the temporal shift issue caused by the rapidly-evolving nature of news data in practice,…
In Twitter, and other microblogging services, the generation of new content by the crowd is often biased towards immediacy: what is happening now. Prompted by the propagation of commentary and information through multiple mediums, users on…
Keeping the performance of language technologies optimal as time passes is of great practical interest. We study temporal effects on model performance on downstream language tasks, establishing a nuanced terminology for such discussion and…
Predicting the popularity of online content is a fundamental problem in various applications. One practical challenge takes roots in the varying length of observation time or prediction horizon, i.e., a good model for popularity prediction…
While most conversational AI systems focus on textual dialogue only, conditioning utterances on visual context (when it's available) can lead to more realistic conversations. Unfortunately, a major challenge for incorporating visual context…
Test-time adaptation, which enables models to generalize to diverse data with unlabeled test samples, holds significant value in real-world scenarios. Recently, researchers have applied this setting to advanced pre-trained vision-language…
For high-resource languages like English, text classification is a well-studied task. The performance of modern NLP models easily achieves an accuracy of more than 90% in many standard datasets for text classification in English (Xie et…
We propose a novel information bottleneck (IB) method named Drop-Bottleneck, which discretely drops features that are irrelevant to the target variable. Drop-Bottleneck not only enjoys a simple and tractable compression objective but also…
Social media has become an important tool to share information about crisis events such as natural disasters and mass attacks. Detecting actionable posts that contain useful information requires rapid analysis of huge volume of data in…
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…
Recent Vision-Language Pretrained (VLP) models have become the backbone for many downstream tasks, but they are utilized as frozen model without learning. Prompt learning is a method to improve the pre-trained VLP model by adding a…
With the widespread deployment of deep learning models, they influence their environment in various ways. The induced distribution shifts can lead to unexpected performance degradation in deployed models. Existing methods to anticipate…
To aid a variety of research studies, we propose TWIROLE, a hybrid model for role-related user classification on Twitter, which detects male-related, female-related, and brand-related (i.e., organization or institution) users. TWIROLE…