Most open-domain dialogue systems suffer from forgetting important
infor...
Zero-shot transfer learning for Dialogue State Tracking (DST) helps to h...
Dense retrieval is widely used for entity linking to retrieve entities f...
Despite the remarkable success of pre-trained language models (PLMs), th...
Visual Question Answering (VQA) models are prone to learn the shortcut
s...
Models for Visual Question Answering (VQA) often rely on the spurious
co...
Conversational Causal Emotion Entailment aims to detect causal utterance...
In zero-shot multilingual extractive text summarization, a model is typi...
Recent studies on the lottery ticket hypothesis (LTH) show that pre-trai...
Modeling of relation pattern is the core focus of previous Knowledge Gra...
Knowledge Graph Embedding (KGE) aims to learn representations for entiti...
User cold-start recommendation is a long-standing challenge for recommen...
While numerous approaches have been developed to embed graphs into eithe...
Document-level RE requires reading, inferring and aggregating over multi...
User identity linkage is a task of recognizing the identities of the sam...
Entity linking is the task of aligning mentions to corresponding entitie...