What can knowledge bring to machine learning?—a survey of low-shot learning for structured data

Y Hu, A Chapman, G Wen, DW Hall - ACM Transactions on Intelligent …, 2022 - dl.acm.org
Supervised machine learning has several drawbacks that make it difficult to use in many
situations. Drawbacks include heavy reliance on massive training data, limited …

Zero-shot open entity ty** as type-compatible grounding

B Zhou, D Khashabi, CT Tsai, D Roth - ar** has been studied predominantly in supervised learning fashion,
mostly with task-specific annotations (for coarse types) and sometimes with distant …

Learning network representations

LG Moyano - The European Physical Journal Special Topics, 2017 - Springer
In this review I present several representation learning methods, and discuss the latest
advancements with emphasis in applications to network science. Representation learning is …

Improving event extraction via multimodal integration

T Zhang, S Whitehead, H Zhang, H Li, J Ellis… - Proceedings of the 25th …, 2017 - dl.acm.org
In this paper, we focus on improving Event Extraction (EE) by incorporating visual
knowledge with words and phrases from text documents. We first discover visual patterns …

Genre separation network with adversarial training for cross-genre relation extraction

G Shi, C Feng, L Huang, B Zhang, H Ji… - Proceedings of the …, 2018 - aclanthology.org
Relation Extraction suffers from dramatical performance decrease when training a model on
one genre and directly applying it to a new genre, due to the distinct feature distributions …

Improving fine-grained entity ty** with entity linking

H Dai, D Du, X Li, Y Song - ar** is a challenging problem since it usually involves a relatively large
tag set and may require to understand the context of the entity mention. In this paper, we use …

An empirical study on multiple information sources for zero-shot fine-grained entity ty**

Y Chen, H Jiang, L Liu, S Shi, C Fan… - Proceedings of the …, 2021 - aclanthology.org
Auxiliary information from multiple sources has been demonstrated to be effective in zero-
shot fine-grained entity ty** (ZFET). However, there lacks a comprehensive understanding …

Dependency and AMR embeddings for drug-drug interaction extraction from biomedical literature

Y Wang, S Liu, M Rastegar-Mojarad, L Wang… - Proceedings of the 8th …, 2017 - dl.acm.org
Drug-drug interaction (DDI) is an unexpected change in a drug's effect on the human body
when the drug and a second drug are co-prescribed and taken together. As many DDIs are …