Conference

Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion
Dynamic topic models track the evolution of topics in sequential documents, which have derived various applications like trend …
Towards the TopMost: A Topic Modeling System Toolkit
Topic models have a rich history with various applications and have recently been reinvigorated by neural topic modeling. However, …
UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages
In this paper, we introduce UniBridge (Cross-Lingual Transfer Learning with Optimized Embeddings and Vocabulary), a comprehensive …
Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives
Knowledge Base Question Answering (KBQA) aims to answer natural language questions over large-scale knowledge bases (KBs), which can be …
Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives
Humans use multiple senses to comprehend the environment. Vision and language are two of the most vital senses since they allow us to …
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
Recently, various parameter-efficient fine-tuning (PEFT) strategies for application to language models have been proposed and …
Historical Embedding-Guided Efficient Large-Scale Federated Graph Learning
Graph convolutional networks (GCNs) are promising for graph learning tasks. For privacy-preserving graph learning tasks involving …
KDMCSE: Knowledge Distillation Multimodal Sentence Embeddings with Adaptive Angular margin Contrastive Learning
Standard extractive systems suffer from the lack of gold training signals since existing corpora solely provide document and …
KDMCSE: Knowledge Distillation Multimodal Sentence Embeddings with Adaptive Angular margin Contrastive Learning
Previous work on multimodal sentence embedding has proposed multimodal contrastive learning and achieved promising results. However, by …
SemRoDe: Macro Adversarial Training to Learn Representations that are Robust to Word-Level Attacks
Language models (LMs) are indispensable tools for natural language processing tasks, but their vulnerability to adversarial attacks …