We describe a novel approach for cross-domain recommendation for research collaboration. We first constructed a large Neo4j graph database representing authors, their expertise, current collaborations, and general biomedical knowledge. This information comes from MEDLINE and from semantic relations extracted with SemRep. Then, by using an extended literature-based discovery paradigm, implemente...

In this paper we present a method for unsupervised semantic role induction which we formalize as a graph partitioning problem. Argument instances of a verb are represented as vertices in a graph whose edge weights quantify their role-semantic similarity. Graph partitioning is realized with an algorithm that iteratively assigns vertices to clusters based on the cluster assignments of neighboring...

Mapping data to a shared domain ontology is a key step in publishing semantic content on the Web. Most of the work on automatically mapping structured and semi-structured sources to ontologies focuses on semantic labeling, i.e., annotating data fields with ontology classes and/or properties. However, a precise mapping that fully recovers the intended meaning of the data needs to describe the se...

Graph Neural Networks (GNNs) such as Convolutional (GCNs) can effectively learn node representations via aggregating neighbors based on the relation graph. However, despite a few exceptions, most of previous work in this line does not consider topical semantics underlying edges, making less effective and learned between nodes hard to explain. For instance, current GNNs make us usually don’t kno...

Recently, pre-trained language representation models such as bidirectional encoder representations from transformers (BERT) have been performing well in commonsense question answering (CSQA). However, there is a problem that the do not directly use explicit information of knowledge sources existing outside. To augment this, additional methods knowledge-aware graph network (KagNet) and multi-hop...

This paper presents a graph-based method for all-word word sense disambiguation of biomedical texts using semantic relatedness as edge weight. Semantic relatedness is derived from a term-topic co-occurrence matrix. The sense inventory is generated by the MetaMap program. Word sense disambiguation is performed on a disambiguation graph via a vertex centrality measure. The proposed method achieve...

Motivated by the task of semantic parsing, we describe a transition system that generalizes standard transition-based dependency parsing techniques to generate a graph rather than a tree. Our system includes a cache with fixed size m, and we characterize the relationship between the parameter m and the class of graphs that can be produced through the graph-theoretic concept of tree decompositio...

We share the implementation details and testing results for video retrieval system based exclusively on features extracted by convolutional neural networks. We show that deep learned features might serve as universal signature for semantic content of video useful in many search and retrieval tasks. We further show that graph-based storage structure for video index allows to efficiently retrievi...