A hybrid approach to concept extraction and recognition-based matching in the domain of human resources

  title={A hybrid approach to concept extraction and recognition-based matching in the domain of human resources},
  author={Daniel Crow and John B. DeSanto},
  journal={16th IEEE International Conference on Tools with Artificial Intelligence},
  • Daniel Crow, J. DeSanto
  • Published 15 November 2004
  • Economics
  • 16th IEEE International Conference on Tools with Artificial Intelligence
We describe the Convex system for extracting concepts from resumes and subsequently matching the best qualified candidates to jobs. A blend of knowledge-based and speculative concept extraction provides high quality results even outside the scope of the built-in knowledge. A comparison test shows the results found by Convex are significantly better than those found by engines using a keyword or statistical conceptual approach. 

Tables from this paper

Enhancing biomedical concept extraction using semantic relationship weights
A new approach to biomedical Concept Extraction is proposed using semantic features of concept graphs that represent full-text documents by graphs and map biomedical terms to predefined ontology concepts to improve the ranking process of potential key concepts.
Analysis and shortcomings of e-recruitment systems: Towards a semantics-based approach addressing knowledge incompleteness and limited domain coverage
An e-recruitment framework addressing current shortcomings through the use of multiple cooperative semantic resources, feature extraction techniques and skill relatedness measures is detailed.
Extracting biomedical concepts from fulltext by relative importance in a graph model
A novel approach to biomedical concept extraction is proposed by adopting a ranking algorithm of relative importance in concept graphs whose nodes and edges are determined by named entity recognition and UMLS Semantic Network.
Concept graphs: Applications to biomedical text categorization and concept extraction
This study explores the representation of text docu ments using concept graphs that are constructed with the help of a domain ontology and demonstrates how the relati onships extracted from text and captured in graph structures can be used to improve the performance of the aforementioned applications.
Exploring concept graphs for biomedical literature mining
  • Min Song
  • Computer Science
    2015 International Conference on Big Data and Smart Computing (BIGCOMP)
  • 2015
A biomedical concept extraction technique based on a ranking algorithm of concept graphs and a close look at the properties of the network to examine how concepts are related to each other and what concept plays a dominant role in the network.
Expert locator using concept linking
The issue of expert finding in educational and research domain is addressed and a novel method for expert finding using concept linking is described, which can outperform the baseline approach.
A Matching Approach Based on Term Clusters for eRecruitment
A system that extracts data from resumes and jobs is described to generate a matching system that provides job applicants with the best jobs to match their qualifications and also provides companies to find the best fit for their job advertisement.
Stopwords in Technical Language Processing
This work rigorously identifies generic, insignificant, uninformative stopwords in engineering texts beyond the stopword in general texts, based on the synthesis of alternative statistical measures such as term frequency, inverse document frequency, and entropy, and curating a stopwords dataset ready for technical language processing applications.
Semantic information integration and question answering based on pervasive agent ontology
Design and implementation of knowledge base for target recognition in remote sensing images
The effectiveness of the presented knowledge base shows the good prospect of the application of knowledge base in remote sensing image processing domain and makes the whole recognition system more flexible and more generic than those systems without knowledge base.


Fully Automatic Acquisition of Taxonomic Knowledge from Large Corpora of Texts: Limited Syntax Knowledge Representation System Based on Natural Language
A new method for fully automatic knowledge acquisition from large corpora of unseen texts that allows one to acquire large quantities of high quality general-purpose knowledge and practically eliminates costly and error-prone human pre&post-processing.
Indexing by Latent Semantic Analysis
A new method for automatic indexing and retrieval to take advantage of implicit higher-order structure in the association of terms with documents (“semantic structure”) in order to improve the detection of relevant documents on the basis of terms found in queries.
Spotting and Discovering Terms through Natural Language Processing
Christian Jacquemin shows how the power of natural language processing (NLP) can be used to advance text indexing and information retrieval (IR) and provides a comprehensive account of the method and implementation of this innovative retrieval technique for text processing.
Enriching the Knowledge Sources Used in a Maximum Entropy Part-of-Speech Tagger
This paper presents results for a maximum-entropy-based part of speech tagger, which achieves superior performance principally by enriching the information sources used for tagging by incorporating these features: more extensive treatment of capitalization for unknown words, and features for the disambiguation of the tense forms of verbs.
Book review: Machine Learning, Neural and Statistical Classification Edited by D. Michie, D.J. Spiegelhalter and C.C. Taylor (Ellis Horwood Limited, 1994)
This well-edited book provides an up-to-date review of different approaches to classification, compares their performance on a wide range of challenging datasets, and draws conclusions on their applicability to realistic industrial problems.
Knowledge modeling at the millennium : The design and evolution of Protégé-2000
An overview of the evolution of Protégé is given, examining the methodological assumptions underlying the original ProtÉgé system and discussing the ways in which the methodology has changed over time.
The PageRank Citation Ranking : Bringing Order to the Web
This paper describes PageRank, a mathod for rating Web pages objectively and mechanically, effectively measuring the human interest and attention devoted to them, and shows how to efficiently compute PageRank for large numbers of pages.
Machine Learning, Neural and Statistical Classification
Survey of previous comparisons and theoretical work descriptions of methods dataset descriptions criteria for comparison and methodology (including validation) empirical results machine learning on
Intelligent high-volume text processing using shallow, domain-specific techniques