What can knowledge bring to machine learning?—a survey of low-shot learning for structured data
Supervised machine learning has several drawbacks that make it difficult to use in many
situations. Drawbacks include heavy reliance on massive training data, limited …
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 …
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 …
advancements with emphasis in applications to network science. Representation learning is …
Improving event extraction via multimodal integration
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 …
knowledge with words and phrases from text documents. We first discover visual patterns …
Genre separation network with adversarial training for cross-genre relation extraction
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 …
one genre and directly applying it to a new genre, due to the distinct feature distributions …
Improving fine-grained entity ty** with entity linking
An empirical study on multiple information sources for zero-shot fine-grained entity ty**
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 …
shot fine-grained entity ty** (ZFET). However, there lacks a comprehensive understanding …
Dependency and AMR embeddings for drug-drug interaction extraction from biomedical literature
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 …
when the drug and a second drug are co-prescribed and taken together. As many DDIs are …