Robust named entity disambiguation with random walks University of Alberta | Publication | 2018-06-01 | |
Matching Ré sumés to Job Descriptions with Stacked Models University of Alberta | Publication | 2018-01-01 | |
Leveraging Wikipedia Table Schemas for Knowledge Graph Augmentation University of Alberta | Publication | 2018-01-01 | |
Accurate fact harvesting from natural language text in wikipedia with Lector University of Alberta | Publication | 2016-01-01 | |
Hadoop energy consumption reduction with hybrid HDFS University of Alberta | Publication | 2016-01-01 | |
Relationship Queries on Extended Knowledge Graphs University of Alberta | Publication | 2016-01-01 | |
Hadoop branching: Architectural impacts on energy and performance University of Alberta | Publication | 2015-12-01 | |
Identifying Controversial Wikipedia Articles Using Editor Collaboration Networks University of Alberta | Publication | 2015-03-01 | |
Inferencing in information extraction: Techniques and applications University of Alberta | Publication | 2015-04-01 | |
Entity linking with a unified semantic representation University of Alberta | Publication | 2014-01-01 | |
Robust Entity Linking via Random Walks University of Alberta | Publication | 2014-01-01 | |
Using triads to identify local community structure in social networks University of Alberta | Publication | 2014-08-01 | |
Sentiment Analysis for Streams of Web Data University of Alberta | Publication | 2014-01-01 | |
Automatically Training Form Classifiers University of Alberta | Publication | 2013-01-01 | |
Shallow Information Extraction for the knowledge Web University of Alberta | Publication | 2013-04-01 | |
Prequery Discovery of Domain-Specific Query Forms: A Survey University of Alberta | Publication | 2013-08-01 | |
Identifying controversial articles in Wikipedia University of Alberta | Publication | 2012-01-01 | |
Extracting information networks from the blogosphere University of Alberta | Publication | 2012-09-01 | |
Leveraging editor collaboration patterns in wikipedia University of Alberta | Publication | 2012-01-01 | |
Access Control Policy Translation, Verification, and Minimization within Heterogeneous Data Federations University of Alberta | Publication | 2011-11-01 | |
Generating Synthetic Database Schemas for Simulation Purposes University of Alberta | Publication | 2011-01-01 | |
Efficient Top-k Approximate Subtree Matching in Small Memory University of Alberta | Publication | 2011-08-01 | |
Towards identifying arguments in Wikipedia pages University of Alberta | Publication | 2011-01-01 | |
Analyzing natural-language artifacts of the software process University of Alberta | Publication | 2010-09-01 | |
Exploring and visualizing academic social networks University of Alberta | Publication | 2010-01-01 | |
Incorporating global information into named entity recognition systems using relational context University of Alberta | Publication | 2010-01-01 | |
Access control policy translation and verification within heterogeneous data federations University of Alberta | Publication | 2010-01-01 | |
TASM : Top-k Approximate Subtree Matching University of Alberta | Publication | 2010-03-01 | |
A framework for automatic schema mapping verification through reasoning University of Alberta | Publication | 2010-01-01 | |
An environment for building, exploring and querying academic social networks University of Alberta | Publication | 2009-01-01 | |
Optimizing XML Compression University of Alberta | Publication | 2009-01-01 | |
FleDEx University of Alberta | Publication | 2007-01-01 | |
Adaptive record extraction from web pages University of Alberta | Publication | 2007-01-01 | |
Declarative generation of synthetic XML data University of Alberta | Publication | 2006-01-01 | |
Studying the XML Web: Gathering Statistics from an XML Sample University of Alberta | Publication | 2006-06-01 | |
Goals and benchmarks for autonomic configuration recommenders University of Alberta | Publication | 2005-01-01 | |
The XML web University of Alberta | Publication | 2003-01-01 | |
Neural Fine-Grained Entity Type Classification with Hierarchy-Aware LossThe 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 are thus susceptible to noisy labels that can be out-of-context or overly-specific for the training sentence. Previous methods that attempt to address these issues do so with heuristics or with the help of hand-crafted features. Instead, we propose an end-to-end solution with a neural network model that uses a variant of cross-entropy loss function to handle out-of-context labels, and hierarchical loss normalization to cope with overly-specific ones. Also, previous work solve FETC a multi-label classification followed by ad-hoc post-processing. In contrast, our solution is more elegant: we use public word embeddings to train a single-label that jointly learns representations for entity mentions and their context. We show experimentally that our approach is robust against noise and consistently outperforms the state-of-the-art on established benchmarks for the task.", University of Alberta | Publication | 2018-06-01 | |
Connecting Language and Knowledge with Heterogeneous Representations for Neural Relation ExtractionKnowledge Bases (KBs) require constant updating to reflect changes to the world they represent. For general purpose KBs, this is often done through Relation Extraction (RE), the task of predicting KB relations expressed in text mentioning entities known to the KB. One way to improve RE is to use KB Embeddings (KBE) for link prediction. However, despite clear connections between RE and KBE, little has been done toward properly unifying these models systematically. We help close the gap with a framework that unifies the learning of RE and KBE models leading to significant improvements over the state-of-the-art in RE. The code is available at https://github.com/billy-inn/HRERE.", University of Alberta | Publication | 2019-06-01 | |
Detecting and Correcting Typing Errors in DBpedia University of Alberta | Publication | 2019-01-01 | |
KnowledgeNet: A Benchmark Dataset for Knowledge Base PopulationKnowledgeNet is a benchmark dataset for the task of automatically populating a knowledge base (Wikidata) with facts expressed in natural language text on the web. KnowledgeNet provides text exhaustively annotated with facts, thus enabling the holistic end-to-end evaluation of knowledge base population systems as a whole, unlike previous benchmarks that are more suitable for the evaluation of individual subcomponents (e.g., entity linking, relation extraction). We discuss five baseline approaches, where the best approach achieves an F1 score of 0.50, significantly outperforming a traditional approach by 79\% (0.28). However, our best baseline is far from reaching human performance (0.82), indicating our dataset is challenging. The KnowledgeNet dataset and baselines are available at https://github.com/diffbot/knowledge-net", University of Alberta | Publication | 2019-11-01 | Filipe Mesquita, Matteo Cannaviccio, Jordan Schmidek, Paramita Mirza, Denilson Barbosa |
Knowledge Graph Embedding for Link Prediction: A Comparative Analysis University of Alberta | Publication | 2020-01-01 | Andrea Rossi, Donatella Firmani, Antonio Matinata, Paolo Merialdo, Denilson Barbosa |
GrCluster: a score function to model hierarchy in knowledge graph embeddings University of Alberta | Publication | 2020-01-01 | Varun Ranganathan, Siddharth Suresh, Yash Mathur, Natarajan Subramanyam, Denilson Barbosa |
Understanding DevOps Education with Grounded Theory University of Alberta | Publication | 2020-01-01 | |
Neural Relation Extraction on Wikipedia Tables for Augmenting Knowledge Graphs University of Alberta | Publication | 2020-01-01 | |
Detection and Identification of Obfuscated Obscene Language with Character Level Transformers University of Alberta | Publication | 2021-01-01 | |