[cardResume jobtitle=”Research Software Developer” company=”IBM Watson Lab Services, India” date=”August 2013 – present”] I work on NLP Modeling team of the Watson Oncology Expert Advisor (OEA), the Watson solution for the MD Anderson Cancer Center, the world’s leading cancer hospital. We work closely with the doctors to annotate complex medical concepts that influence Watson’s decision. Using the large patient data Watson suggests which clinical trial best suits the patient by providing supporting evidence. This is an integral part in gaining the Doctor’s confidence on Watson’s cognitive ability.
• NLP modeling: Mine concepts from unstructured text in medical domain. Develop and enhance lexicon using machine learning and rule-based grammar for new concepts.
• Java development: Add functionality to Watson OEA through eclipse based development.
• UIMA framework: Configure XML and Java resources for NLP annotators in a UIMA pipeline.
• Analysis: In-depth analysis of the leukemia patients to improve precision & recall.
• Innovation: As a part of lab services team we built innovative products namely Watson-I (Information Extraction from charts and graphs in the document) and Extracting embedded tables from the PDF documents.
[cardResume jobtitle=”Research Engineer” company=”Lexical Computing Ltd., UK” date=”August 2010 – August 2013″] LCL is a research company which works at the intersection of corpus and computational linguistics. Our majority of tasks revolve around building web corpora for various domains and languages. As a part of research we collaborated in PRESEMT:“Pattern REcognition-based Statistically Enhanced MT” on “Comparable Corpora BootCat” and “Hierarchy of Domains”. We are currently working on “TEDDCLOG” which is an automatic gap-fill question generation system for language teaching, this is done under the supervision of Prof. Simon Smith.
[cardResume jobtitle=”Research Assistant” company=”LTRC, IIIT Hyderabad” date=”May 2006 – July 2011″] LTRC is one of the top NLP research institutes in India. I have been acquainted in multiple areas of NLP and Machine Learning while working with different research groups. Majority of my work involved Machine Translation (MT), tools for less privileged languages, dialog systems, part-of-speech tagging and chunking for Indian languages. Some major contributions to LTRC involves building shallow parser for 9 Indian languages and a key role in SAMPARK a Govt. of India, Ministry of IT project for Indian language MT.
[cardResume jobtitle=”Teaching Assitant” company=”Artificial Intelligence, IIIT Hyderabad” date=”Dec 2006 – April 2007″] Assist the Professor in managing a class of 180 students and plan tutorial/assignments for the students. Correct the answer sheets, assignments and perform other tasks related to course website.
The following are my skills and their levels respectively.
[cardSkill title=”Python” skill=”four”] [/cardSkill] [cardSkill title=”C++” skill=”three”] [/cardSkill] [cardSkill title=”R” skill=”two”] [/cardSkill] [cardSkill title=”Scrapy” skill=”three”] [/cardSkill] [cardSkill title=”NLTK” skill=”three”] [/cardSkill] [cardSkill title=”Open NLP” skill=”two”] [/cardSkill] [cardSkill title=”Weka” skill=”two”] [/cardSkill]