activity
20202023
most citedGLocal-K: Global and Local Kernels for Recommender Systems

41 citations · 68 across the 12 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2023

MC-DRE: Multi-Aspect Cross Integration for Drug Event/Entity Extraction

Jie Yang, Soyeon Caren Han, Siqu Long +2

Extracting meaningful drug-related information chunks, such as adverse drug events (ADE), is crucial for preventing morbidity and saving many lives. Most ADEs are reported via an u…

cs.CL2023

Tri-level Joint Natural Language Understanding for Multi-turn Conversational Datasets

Henry Weld, Sijia Hu, Siqu Long +2

Natural language understanding typically maps single utterances to a dual level semantic frame, sentence level intent and slot labels at the word level. The best performing models…

cs.CL20226 cited

ME-GCN: Multi-dimensional Edge-Embedded Graph Convolutional Networks for Semi-supervised Text Classification

Kunze Wang, Soyeon Caren Han, Siqu Long +1

Compared to sequential learning models, graph-based neural networks exhibit excellent ability in capturing global information and have been used for semi-supervised learning tasks.…

cs.CL20226 cited

Understanding Graph Convolutional Networks for Text Classification

Soyeon Caren Han, Zihan Yuan, Kunze Wang +2

Graph Convolutional Networks (GCN) have been effective at tasks that have rich relational structure and can preserve global structure information of a dataset in graph embeddings.…

cs.CL2022

Bi-directional Joint Neural Networks for Intent Classification and Slot Filling

Soyeon Caren Han, Siqu Long, Huichun Li +2

Intent classification and slot filling are two critical tasks for natural language understanding. Traditionally the two tasks proceeded independently. However, more recently joint…

cs.CL2021

CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection

Henry Weld, Guanghao Huang, Jean Lee +6

Traditional toxicity detection models have focused on the single utterance level without deeper understanding of context. We introduce CONDA, a new dataset for in-game toxic langua…