Related papers: VIBE: Topic-Driven Temporal Adaptation for Twitter…

Recent generative models have achieved remarkable progress in image editing. However, existing systems and benchmarks remain largely text-guided. In contrast, human communication is inherently multimodal, where visual instructions such as…

Language use differs between domains and even within a domain, language use changes over time. For pre-trained language models like BERT, domain adaptation through continued pre-training has been shown to improve performance on in-domain…

We introduce an improved variational autoencoder (VAE) for text modeling with topic information explicitly modeled as a Dirichlet latent variable. By providing the proposed model topic awareness, it is more superior at reconstructing input…

Social media has provided a platform for users to gather and share information and stay updated with the news. Such networks also provide a platform to users where they can engage in conversations. However, such micro-blogging platforms…

Emergent communication research often focuses on optimizing task-specific utility as a driver for communication. However, human languages appear to evolve under pressure to efficiently compress meanings into communication signals by…

Social media such as Twitter provide valuable information to crisis managers and affected people during natural disasters. Machine learning can help structure and extract information from the large volume of messages shared during a crisis;…

This paper investigates task-oriented communication for edge inference, where a low-end edge device transmits the extracted feature vector of a local data sample to a powerful edge server for processing. It is critical to encode the data…

Despite its importance, the time variable has been largely neglected in the NLP and language model literature. In this paper, we present TimeLMs, a set of language models specialized on diachronic Twitter data. We show that a continual…

Language is constantly changing and evolving, leaving language models to become quickly outdated. Consequently, we should continuously update our models with new data to expose them to new events and facts. However, that requires additional…

This study proposes a framework that extends existing time-coding time-to-first-spike spiking neural network (SNN) models to allow processing information changing over time. We explain spike propagation through a model with multiple input…

We describe TweeTIME, a temporal tagger for recognizing and normalizing time expressions in Twitter. Most previous work in social media analysis has to rely on temporal resolvers that are designed for well-edited text, and therefore suffer…

Time series forecasting has become an increasingly popular research area due to its critical applications in various real-world domains such as traffic management, weather prediction, and financial analysis. Despite significant…

Benefiting from large-scale pretrained vision language models (VLMs), the performance of visual question answering (VQA) has approached human oracles. However, finetuning such models on limited data often suffers from overfitting and poor…

Various domain users are increasingly leveraging real-time social media data to gain rapid situational awareness. However, due to the high noise in the deluge of data, effectively determining semantically relevant information can be…

Recent advances in sophisticated synthetic speech generated from text-to-speech (TTS) or voice conversion (VC) systems cause threats to the existing automatic speaker verification (ASV) systems. Since such synthetic speech is generated from…

Opinion prediction on Twitter is challenging due to the transient nature of tweet content and neighbourhood context. In this paper, we model users' tweet posting behaviour as a temporal point process to jointly predict the posting time and…

Temporal validity is an important property of text that is useful for many downstream applications, such as recommender systems, conversational AI, or story understanding. Existing benchmarking tasks often require models to identify the…

Identifying adverse and hostile content on the web and more particularly, on social media, has become a problem of paramount interest in recent years. With their ever increasing popularity, fine-tuning of pretrained Transformer-based…

The use of abusive language online has become an increasingly pervasive problem that damages both individuals and society, with effects ranging from psychological harm right through to escalation to real-life violence and even death.…

We present a simple case study, demonstrating that Variational Information Bottleneck (VIB) can improve a network's classification calibration as well as its ability to detect out-of-distribution data. Without explicitly being designed to…