activity
20182021
most citedConnecting Language and Knowledge with Heterogeneous Representations for Neural Relation Extraction

3 citations · 4 across the 3 of their papers we have counts for

collaborators

7 papers

cs.SE2021

An empirical evaluation of the usefulness of Tree Kernels for Commit-time Defect Detection in large software systems

Hareem Sahar, Yuxin Liu, Abram Hindle +1

Defect detection at commit check-in time prevents the introduction of defects into software systems. Current defect detection approaches rely on metric-based models which are not v…

cs.DB20211 cited

Typing Errors in Factual Knowledge Graphs: Severity and Possible Ways Out

Peiran Yao, Denilson Barbosa

Factual knowledge graphs (KGs) such as DBpedia and Wikidata have served as part of various downstream tasks and are also widely adopted by artificial intelligence research communit…

cs.IR2020

An Annotated Corpus of Webtables for Information Extraction Tasks

Erin Macdonald, Denilson Barbosa

Information Extraction is a well-researched area of Natural Language Processing with applications in web search and question answering concerned with identifying entities and relat…

cs.LG2020

Knowledge Graph Embedding for Link Prediction: A Comparative Analysis

Andrea Rossi, Donatella Firmani, Antonio Matinata +2

Knowledge Graphs (KGs) have found many applications in industry and academic settings, which in turn, have motivated considerable research efforts towards large-scale information e…

cs.CL20193 cited

Connecting Language and Knowledge with Heterogeneous Representations for Neural Relation Extraction

Peng Xu, Denilson Barbosa

Knowledge Bases (KBs) require constant up-dating to reflect changes to the world they represent. For general purpose KBs, this is often done through Relation Extraction (RE), the t…

cs.CL2018

Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Loss

Peng Xu, Denilson Barbosa

The task of Fine-grained Entity Type Classification (FETC) consists of assigning types from a hierarchy to entity mentions in text. Existing methods rely on distant supervision and…