activity
20202025
most citedGraph Neural Networks for Text Classification: A Survey

70 citations · 357 across the 62 of their papers we have counts for

collaborators
Showing 2021Show all

6 papers · 1 filter

cs.IR2021★ 41 cited

GLocal-K: Global and Local Kernels for Recommender Systems

Soyeon Caren Han, Taejun Lim, Siqu Long +2

Recommender systems typically operate on high-dimensional sparse user-item matrices. Matrix completion is a very challenging task to predict one's interest based on millions of oth…

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…

cs.CL2021★ 7 cited

FedNLP: An interpretable NLP System to Decode Federal Reserve Communications

Jean Lee, Hoyoul Luis Youn, Nicholas Stevens +2

The Federal Reserve System (the Fed) plays a significant role in affecting monetary policy and financial conditions worldwide. Although it is important to analyse the Fed's communi…

cs.CL2021★ 36 cited

Local Interpretations for Explainable Natural Language Processing: A Survey

Siwen Luo, Hamish Ivison, Caren Han +1

As the use of deep learning techniques has grown across various fields over the past decade, complaints about the opaqueness of the black-box models have increased, resulting in an…

cs.CL2021★ 25 cited

A survey of joint intent detection and slot-filling models in natural language understanding

H. Weld, X. Huang, S. Long +2

Intent classification and slot filling are two critical tasks for natural language understanding. Traditionally the two tasks have been deemed to proceed independently. However, mo…

cs.IR2021★ 16 cited

A Survey on Extraction of Causal Relations from Natural Language Text

Jie Yang, Soyeon Caren Han, Josiah Poon

As an essential component of human cognition, cause-effect relations appear frequently in text, and curating cause-effect relations from text helps in building causal networks for…