Sandya Mannarswamy

Research Scientist


Sandya Mannarswamy is a Research Scientist in the Text & Graph Analytics area within the Data Analytics Lab at Conduent Labs India. Her research interests lie in the areas of natural language processing and text analytics. She is currently focussing on applying text mining and natural language processing to healthcare analytics, urban informatics and customer care analytics in Conduent Labs India. Her broad research vision is enabling machine understanding of textual content on par with human understanding. Sandya believes that collaboration is a key component of good research, and is interested in working with researchers and development engineers, both within Conduent, and in academia.

Prior to joining Xerox in 2015, She worked as a master technologist in Hewlett Packard India Software (HP), where her work spanned programming languages, compilers and file systems. She holds a few patents in these areas and a number of publications in external conferences. She has been voted as a prolific inventor at HP and has won a number of recognitions for innovation at HP. Her earlier research has focused on improving application performance and scalability on high-end server systems for single and multithreaded enterprise applications using compiler analysis and optimizations. She focussed on developing novel compiler optimizations to improve cache performance of applications by means of data layout transformations. She has a number of publications and patents to her credit.

Contact:

• Email: Sandya [dot] Mannarswamy [at] conduent [dot] com


  • 1. Shrestha Mundra, Manjira Sinha, Sandya Mannarswamy, Anirban Sen. Fine-grained Emotion Detection in Contact Center Chat Utterances. The Pacific-Asia Conference on Knowledge Discovery and Data Mining PAKDD 2017

  • 2. Anirban Sen, Sandya Mannarswamy, Manjira Sinha. Multi-task Representation Learning for Enhanced Emotion Categorization in Short Text. The Pacific-Asia Conference on Knowledge Discovery and Data Mining PAKDD 2017

  • 3. Shreshtha Mundra, Manjira Sinha, Sandya Mannarswamy, Anirban Sen and Shourya Roy , “Embedding Learning of Figurative Phrases for Emotion Classification in Micro-Blog Texts”, in ACM IKDD Conference on Data Sciences, 2017

  • 4. Failure Atomic Update of User Data File, Verma, Mendez, Mannarswamy et al, USENIX FAST 2015.

  • 5. Sandya S. Mannarswamy and R. Govindarajan, Reconciling Transactional Conflicts with Compiler's Help, In CGO 2012: Proceedings of the International Symposium on Code Generation and Optimization, San Jose, CA, USA, 2012.

  • 6. Sandya S. Mannarswamy and R. Govindarajan, Making STMs Cache Friendly with Compiler's Help, In the Proceedings of the 20th international conference on Parallel architectures and compilation techniques (PACT '11), Galveston, US, September 2011. Acceptance Rate: 16%

  • 7. Sandya S. Mannarswamy and R. Govindarajan, A Variable Granularity Access Tracking Scheme for Improving the Performance of Software Transactional Memory, In the Proceedings of the 25th IEEE International Parallel and Distributed Processing Symposium (IPDPS-2011), Alaska, USA, May 2011. Acceptance Rate: 19.6%

  • 8. Sandya S. Mannarswamy and R. Govindarajan, Analysing Cache Performance Bottlenecks of STM Applications and Addressing them with Compiler's Help, In the Proceedings of the 19th international conference on Parallel architectures and compilation techniques, Vienna, Austria, September 2010 Acceptance Rate: 17.29%

  • 9. Sandya S. Mannarswamy and R. Govindarajan, Handling Conflicts with Compiler's Help in Software Transactional Memory Systems, In the Proceedings of the 2010 39th International Conference on Parallel Processing (ICPP-2010), September 2010. Acceptance Rate: 32%

  • 10. Sandya S. Mannarswamy, Dhruva R. Chakrabarti, Kaushik Rajan, and Sujoy Saraswati, Compiler Aided Selective Lock Assignment for Improving the Performance of Software Transactional Memory, In the Proceedings of the 15th ACM SIGPLAN symposium on Principles and practice of parallel programming (PPoPP-2010)}, Bangalore, India, January 2010. Acceptance Rate: 16.7%

  • 11. Sandya S. Mannarswamy and R. Govindarajan, Region Based Structure Layout Optimization by Selective Data Copying, In the Proceedings of the 18th International Conference on Parallel Architectures and Compilation Techniques, (PACT-2009), Washington, DC, USA, September 2009. Acceptance Rate: 18.09%

  • 12. Easwaran Raman, Robert Hundt, and Sandya S. Mannarswamy, Structure Layout Optimization for Multithreaded Programs, CGO-2007, Proceedings of the 2007 International Symposium on Code Generation and Optimization , March 2007. Acceptance Rate: 42.86%

  • 13. Nathaniel McIntosh, Sandya Mannarswamy, and Robert Hundt, Whole program optimization of global variable layout, in PACT ’06: Proceedings of the 15th International Conference on Parallel Architectures and Compilation Techniques, (Seattle, WA, USA), IEEE Computer Society, 2006. Acceptance Rate: 25%