Holistic label correction for noisy multi-label classification
Multi-label classification aims to learn classification models from instances associated with
multiple labels. It is pivotal to learn and utilize the label dependence among multiple labels …
multiple labels. It is pivotal to learn and utilize the label dependence among multiple labels …
Event-event relation extraction using probabilistic box embedding
To understand a story with multiple events, it is important to capture the proper relations
across these events. However, existing event relation extraction (ERE) framework regards it …
across these events. However, existing event relation extraction (ERE) framework regards it …
Modeling label space interactions in multi-label classification using box embeddings
Multi-label classification is a challenging structured prediction task in which a set of output
class labels are predicted for each input. Real-world datasets often have natural or latent …
class labels are predicted for each input. Real-world datasets often have natural or latent …
Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships
Modeling and visualizing relationships between tasks or datasets is an important step
towards solving various meta-tasks such as dataset discovery multi-tasking and transfer …
towards solving various meta-tasks such as dataset discovery multi-tasking and transfer …
Locality sensitive hashing in fourier frequency domain for soft set containment search
I Roy, R Agarwal, S Chakrabarti… - Advances in Neural …, 2023 - proceedings.neurips.cc
In many search applications related to passage retrieval, text entailment, and subgraph
search, the query and each'document'is a set of elements, with a document being relevant if …
search, the query and each'document'is a set of elements, with a document being relevant if …
Insert or Attach: Taxonomy Completion via Box Embedding
Taxonomy completion, enriching existing taxonomies by inserting new concepts as parents
or attaching them as children, has gained significant interest. Previous approaches embed …
or attaching them as children, has gained significant interest. Previous approaches embed …
Representing spatial trajectories as distributions
D Suris Coll-Vinent, C Vondrick - Advances in Neural …, 2022 - proceedings.neurips.cc
We introduce a representation learning framework for spatial trajectories. We represent
partial observations of trajectories as probability distributions in a learned latent space …
partial observations of trajectories as probability distributions in a learned latent space …
Representing spatial trajectories as distributions
DS Coll-Vinent, C Vondrick - Advances in Neural Information …, 2022 - openreview.net
We introduce a representation learning framework for spatial trajectories. We represent
partial observations of trajectories as probability distributions in a learned latent space …
partial observations of trajectories as probability distributions in a learned latent space …
Uncertain Knowledge Graph Embedding Using Auxiliary Information
Uncertain knowledge graphs (UKGs) offer a more realistic representation of knowledge by
capturing the uncertainty associated with facts. However, existing UKG embedding methods …
capturing the uncertainty associated with facts. However, existing UKG embedding methods …
Taxonomy Completion with Probabilistic Scorer via Box Embedding
Taxonomy completion, a task aimed at automatically enriching an existing taxonomy with
new concepts, has gained significant interest in recent years. Previous works have …
new concepts, has gained significant interest in recent years. Previous works have …