Natural language understanding typically maps single utterances to a dua...
Compared to general document analysis tasks, form document structure
und...
When a human communicates with a machine using natural language on the w...
We propose a PiggyBack, a Visual Question Answering platform that allows...
Collaborative filtering problems are commonly solved based on matrix
com...
Recognizing the layout of unstructured digital documents is crucial when...
Attention mechanism has been used as an important component across
Visio...
For preventing youth suicide, social media platforms have received much
...
Pretrained models have produced great success in both Computer Vision (C...
Compared to sequential learning models, graph-based neural networks exhi...
Graph Convolutional Networks (GCN) have been effective at tasks that hav...
Intent classification and slot filling are two critical tasks for natura...
Recommender systems typically operate on high-dimensional sparse user-it...
Traditional toxicity detection models have focused on the single utteran...
Online abusive language detection (ALD) has become a societal issue of
i...
Text-to-image multimodal tasks, generating/retrieving an image from a gi...