Project Name

Knowledge engineering


Tab navigation

Knowledge engineering is a discipline that involves the design and implementation of computational tools and solutions that manage of the flow of knowledge to solve complex problems which would normally require a high level of human expertise.

Services companies are evaluated based on the quality and effectiveness of knowledge flow within organizations. We work on technologies for answering questions about complex domains like technical or product support areas. We also develop technologies in the area of Customer Relationship Management (CRM) analytics that provides actionable business insights for customers and operational efficiency. Further, we develop tools for improving productivity of practitioners by effectively reusing the knowledge acquired by practitioners, and knowledge management systems that address the intense and diverse information needs of the pre-sales communities.

Selected projects:

Project Holmes

Create technologies for answering questions about complex domains like technical or product support areas. We are creating advanced algorithms in Natural Language Processing (NLP), Question Answering, Machine Learning and Dialog Processing to create systems that will get the exact information queried by a user in real time.

Voice of Customer Analytics

IBM Voice of Customer Analytics (VoCA) is a managed service in the area of Customer Relationship Management (CRM) analytics that provides actionable business insights for customers and operational efficiency. In VOCA, heterogeneous structured and unstructured data sources like customer profile and transactions, customer satisfaction surveys, call transcripts, agent logs, and activity records are captured and linked together. An IBM Business Analyst analyzes various heterogenous data sources, enabled by advanced analytical capabilities such as data linking, text clustering, text annotation, sentiment mining and predictive modeling, to come up with actionable insights regarding customer churn, first call resolution, key customer satisfaction and dissatisfaction drivers.

Catapult - Effective knowledge management for services

Improving productivity of practitioners is a critical goal for IT services organizations. In large organizations with many teams providing services to different clients, it is important to effectively re-use the knowledge acquired by practitioners.. The IBM team is working on developing a technology for effective knowledge management that will enable practitioners to re-use the knowledge in their day-to-day activities. It will also provide a general framework for analyzing problem data to automatically identify the main challenge areas for the concerned client. This work involves some interesting and challenging problems in the areas of information retrieval, information extraction, machine learning and data management. The IBM Research team works very closely with the technical team in IBM's services unit as well as the services teams that directly support clients.

Ozone

Ozone is a next-generation knowledge management system built to specifically address the intense and diverse information needs of the pre-sales community, which crafts solutions for service engagements. It delivers contextual and targeted content from different data sources as one creates a solution for a new opportunity. Currently, Ozone indexes artifacts created in past opportunities and best practice content present in different IBM wikis and portals. With Ozone, productivity of knowledge workers can increase many fold - they can easily find past opportunities that were similar to current one and then leverage the past artifacts as a starting point; they can also locate experts for help. Moreover, Ozone empowers them to be data-driven and hence improves solution quality. The knowledge workers can validate their assumptions with historical evidence, they can find winning value propositions and gain crucial competitive information. In summary, Ozone helps create winning solutions by delivering insights about the client's needs, the competition's armoury and, most importantly, the breadth of IBM's capabilities.

Highlighted papers:

  • Retrieving Similar Discussion Forum Threads: A Structure based Approach
    Amit Singh, Deepak P, Dinesh Raghu
    ACM International Conference on Research and Development in Information Retrieval (SIGIR), 2012
  • CQC: Question Classification in Community Question Answer Portals
    Amit Singh, Karthik Visweswariah
    Conference on Information and Knowledge Management (CIKM), 2011
  • Entity based Q&A Retrieval
    Amit Singh
    Conference on Empirical Methods on Natural Language Processing and Computational Natural Language Learning (EMNLP), 2012
  • Query suggestions in the absence of Query Logs
    Sumit Bhatia, Debapriyo Majumdar, Prasenjit Mitra
    ACM Special Interest Group on Information Retrieval Conference (SIGIR), 2011
  • Exploiting Coherence for the Simultaneous Discovery of Latent Facets and Associated Sentiments
    Himabindu Lakkaraju, Chiranjib Bhattacharyya, Indrajit Bhattacharya, Srujana Merugu,
    SIAM International Conference on Data Mining (SDM), 2011 (Best Paper Award)
  • A cross-lingual spoken content search system
    Jitendra Ajmera, Ashish Verma
    Conference of the International Speech Communication Association (INTERSPEECH), 2011
  • A Cluster-Level Semi-Supervision Model for Interactive Clustering
    Avinava Dubey, Indrajit Bhattacharya, Shantanu Godbole
    ECML-PKDD 2010
  • A Language Independent Approach to Audio Search
    Vikram Gupta, Jitendra Ajmera, Ashish Verma, Arun Kumar
    Conference of the International Speech Communication Association (INTERSPEECH), 2011
  • Acoustic-Similarity Based Technique to Improve Concept Recognition
    Om D Deshmukh, Shajith Ikbal, Ashish Verma, Etienne Marcheret
    Conference of the International Speech Communication Association (INTERSPEECH), 2011
  • Enabling Analysts in Managed Services for CRM Analytics
    Indrajit Bhattacharya, Shantanu Godbole, Ajay Gupta, Ashish Verma, Jeff, and Kevin English
    KDD 2009

Contact:

Nanda Kambhatla: kambhatlaatin.ibm.com