Search Results for author:
Found 6 papers, 3 papers with code
Explorers at #SMM4H 2023: Enhancing BERT for Health Applications through Knowledge and Model Fusion
An increasing number of individuals are willing to post states and opinions in social media, which has become a valuable data resource for studying human health.
Revisiting Event Argument Extraction: Can EAE Models Learn Better When Being Aware of Event Co-occurrences?
Under this framework, we experiment with 3 different training-inference schemes on 4 datasets (ACE05, RAMS, WikiEvents and MLEE) and discover that via training the model to extract all events in parallel, it can better distinguish the semantic boundary of each event and its ability to extract single event gets substantially improved.
LoTE-Animal: A Long Time-span Dataset for Endangered Animal Behavior Understanding
To break the deadlock, we present LoTE-Animal, a large-scale endangered animal dataset collected over 12 years, to foster the application of deep learning in rare species conservation.
SetGNER: General Named Entity Recognition as Entity Set Generation
Distinguished from the set-prediction NER framework, our method treats each entity as a sequence and is capable of recognizing discontinuous mentions.
Contrastive Learning with Hard Negative Entities for Entity Set Expansion
In addition, we propose the ProbExpan, a novel probabilistic ESE framework utilizing the entity representation obtained by the aforementioned language model to expand entities.
Multi-Graph Convolutional-Recurrent Neural Network (MGC-RNN) for Short-Term Forecasting of Transit Passenger Flow
Spatial dependencies, temporal dependencies, inter-station correlations driven by other latent factors, and exogenous factors bring challenges to the short-term forecasts of passenger flow of urban rail transit networks.
