About Me

Hi I am Bedapudi Praneeth,
I currently work as a Senior NLP Engineer at DeepAffects.

My profiles: Sourcerer Linkedin Medium Github GoodReads

Senior NLP Engineer, DeepAffects, Mumbai

2019 May — present

1. Implemented DeepAffects' Smart Punctuation API and adapted it for time-constrained (more accurate, 50x faster than DeepPunct) ASR use cases. (Including data collection, dockerization of DL models, client libraries and Kuberentes deployments).
2. Built summarization system for conversational data. (Including data collection, building dialogue act prediction models, clustering, dockerization and kuberentes deployments)
3. Built various analytics and metrics (aspect based key-phrase extraction, call scoring, emotion prediction etc.) for DeepAffects' callspot and calleq.
4. Worked on various parts of ASR pipeline (adapting language models for low-resource domains and domain specific phrases, vad etc.).
5. Adapted DeepSegment for FinSBD 2019 shared task (First in French and Close second in English tasks.).
6. Built DeepAffect's Chapter Detection Api (Including image data genetation for chapter type detection, Text Detection and Recognition algorithms and frame level binary search for chapter detection.)

Deep Learning engineer, Reckonsys Tech Labs, Bengaluru

2018 August — 2019 May

1. Built data extraction modules for domain specific, large contracts, that can deal with noisy text (result of OCR).
2. Built document categorization system to categorize and rename hundreds of different types of large documents.
3. Built a NLP module that can extract and cross verify information from multiple legal documents.
4. Built a NER system for domain specific data, with very low amount of training data.
5. Designed and built a novel algorithm, that can extract structured data from different types of tables (multi-line cells, cells separated only by a single space etc.)

Junior Research Associate, Abzooba, Pune

2017 July — 2018 July

1. Implemented graph db to enhance the accuracy and performance of Abzooba's propitiatory NLU engine.
2. Played a major role in moving Abzooba's rule based NER engine to Deep Learning based models.
3. Implemented various techniques to decrease the work load of data labelers.
4. Worked on the NLP and NLU part of various chatbots, which offer various functionality like clothing suggestions, natural language text to MySQL converters etc.

Software Developer Internship, Innoplexus, Pune

2016 May — 2016 July

1. Setted up ElasticSearch (v2.3) production cluster along with ES Shield and Graylog.
2. Wrote high performance modules for data migration from MongoDB to ElasticSearch and Neo4j. (Increased performance of existing modules by a factor of 50-60)
3. Implemented naive spell correction and query auto completion for various fields using ElasticSearch.

Student, IIT Guwahati

2013 — 2017

Graduated from IIT Guwahati, Computer Science and Engineering department in 2017 (B.tech).
My BTP was on Verification of Contract Refinement using Othello Contract Refinement and Analysis under the guidance of Prof. Purandar Bhaduri.