Leveraging sources of collective wisdom on the web for discovering technology synergies

One of the central tasks of R&D strategy and portfolio management at large technology companies and research institutions refers to the identification of technological synergies throughout the organization. These efforts are geared towards saving resources by consolidating scattered expertise, sharing best practices, and reusing available technologies across multiple product lines. In the past, this task has been done in a manual evaluation process by technical domain experts. While feasible, the major drawback of this approach is the enormous effort in terms of availability and time: For a structured and complete analysis every combination of any two technologies has to be rated explicitly. We present a novel approach that recommends technological synergies in an automated fashion, making use of abundant collective wisdom from the Web, both in pure textual form as well as classification ontologies. Our method has been deployed for practical support of the synergy evaluation process within our company. We have also conducted empirical evaluations based on randomly selected technology pairs so as to benchmark the accuracy of our approach, as compared to a group of general computer science technologists as well as a control group of domain experts.

[1]  Filippo Menczer,et al.  Algorithmic detection of semantic similarity , 2005, WWW '05.

[2]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[3]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[4]  David McLean,et al.  An Approach for Measuring Semantic Similarity between Words Using Multiple Information Sources , 2003, IEEE Trans. Knowl. Data Eng..

[5]  Carsten Lutz,et al.  Resasoning about Concepts and Similarity , 2003, Description Logics.

[6]  Pattie Maes,et al.  Social information filtering: algorithms for automating “word of mouth” , 1995, CHI '95.

[7]  Jennifer Widom,et al.  Exploiting hierarchical domain structure to compute similarity , 2003, TOIS.

[8]  Georg Lausen,et al.  Automatic computation of semantic proximity using taxonomic knowledge , 2006, CIKM '06.

[9]  Dekang Lin,et al.  An Information-Theoretic Definition of Similarity , 1998, ICML.

[10]  Luc De Raedt,et al.  Machine Learning: ECML 2001 , 2001, Lecture Notes in Computer Science.

[11]  Graeme Hirst,et al.  Semantic distance in WordNet: An experimental, application-oriented evaluation of five measures , 2004 .

[12]  Peter D. Turney Mining the Web for Synonyms: PMI-IR versus LSA on TOEFL , 2001, ECML.

[13]  Danushka Bollegala,et al.  Measuring semantic similarity between words using web search engines , 2007, WWW '07.

[14]  Sean M. McNee,et al.  Improving recommendation lists through topic diversification , 2005, WWW '05.

[15]  Mehran Sahami,et al.  A web-based kernel function for measuring the similarity of short text snippets , 2006, WWW '06.

[16]  Philip Resnik,et al.  Semantic Similarity in a Taxonomy: An Information-Based Measure and its Application to Problems of Ambiguity in Natural Language , 1999, J. Artif. Intell. Res..

[17]  Carsten Lutz,et al.  Øøøðððù Ððóööøøñ Óö Ööö×óòòòò Óùø Óò Blockin Blockinôø× Òò ××ññððööøý , 2003 .

[18]  Alexander Borgida,et al.  Towards Measuring Similarity in Description Logics , 2005, Description Logics.