We first build a cross-source heterogeneous knowledge graph from customer purchase history and product knowledge graph to jointly learn customer and product embeddings.
We present a study on leveraging multilingual pre-trained generative language models for zero-shot cross-lingual event argument extraction (EAE).
Technology for language generation has advanced rapidly, spurred by advancements in pre-training large models on massive amounts of data and the need for intelligent agents to communicate in a natural manner.
For example, with "add milk to my cart", a customer may refer to a certain organic product, while some customers may want to re-order products they regularly purchase.
The ability to capture complex linguistic structures and long-term dependencies among words in the passage is essential for discourse-level relation extraction (DRE) tasks.
Finally, we propose (1) baseline methods and (2) a new adversarial learning framework for class-agnostic detection that forces the model to exclude class-specific information from features used for predictions.
Ad hominem attacks are those that target some feature of a person's character instead of the position the person is maintaining.
Supervised machine learning models often associate irrelevant nuisance factors with the prediction target, which hurts generalization.
We propose a novel approach to achieving invariance for deep neural networks in the form of inducing amnesia to unwanted factors of data through a new adversarial forgetting mechanism.
We present a systematic study of biases in natural language generation (NLG) by analyzing text generated from prompts that contain mentions of different demographic groups.
Deep neural network models for speech recognition have achieved great success recently, but they can learn incorrect associations between the target and nuisance factors of speech (e. g., speaker identities, background noise, etc.
We present a unified invariance framework for supervised neural networks that can induce independence to nuisance factors of data without using any nuisance annotations, but can additionally use labeled information about biasing factors to force their removal from the latent embedding for making fair predictions.
Finding a template in a search image is one of the core problems many computer vision, such as semantic image semantic, image-to-GPS verification \etc.
Image repurposing is a commonly used method for spreading misinformation on social media and online forums, which involves publishing untampered images with modified metadata to create rumors and further propaganda.
Data representations that contain all the information about target variables but are invariant to nuisance factors benefit supervised learning algorithms by preventing them from learning associations between these factors and the targets, thus reducing overfitting.
We provide guidelines for designing CapsNet discriminators and the updated GAN objective function, which incorporates the CapsNet margin loss, for training CapsuleGAN models.
Conditional Generative Adversarial Networks (cGANs) are generative models that can produce data samples ($x$) conditioned on both latent variables ($z$) and known auxiliary information ($c$).
In this paper, we present a novel deep learning-based approach for assessing the semantic integrity of multimedia packages containing images and captions, using a reference set of multimedia packages.