Saloni Potdar Senior Technical Staff Member and Engineering Manager

About Me

| | | | |

I am a Senior Technical Staff Member and Engineering Manager at IBM Watson where I work on Natural Language Processing and Machine Learning. I design and develop algorithms for IBM's conversational AI product - Watson Assistant. I got my Masters degree at the Language Technologies Institute at Carnegie Mellon University in 2014.

What I’m currently working on


I work on the Natural Language Understanding components which includes intent classification, entity recognition, spellcheck and irrelevant detection. These features are supported across 13 languages and newly introduced universal language feature that supports more languages. The algorithms are designed to be custom-trained for customers globally, deployed at scale with hundreds of thousands of models in production and serves more than 1.9% of the world’s population every month.

Awards & Recognition

  1. Master Inventor
  2. Corporate Award 2021 - Watson Assistant
  3. Outstanding Technical Achievement Award 2021 - State-of-the-art algorithms for intent classification and entity recognition in Watson Assistant
  4. Research AI Accomplishment (A-level) 2020 - Meta-Learning for Low-Resource NLP
  5. Corporate Award 2020 - Language enablement for Watson Services
  6. Women in Leadership Program 2019 - I was one of the 25 women leaders across IBM selected for the fully funded eCornell certificate program
  7. Corporate Award 2018 - Watson Conversation Service
  8. Best of IBM 2018 - Awarded to less than 1000 employees globally contributions to IBM’s business
  9. Eminence and Excellence Award 2017
  10. Outstanding Technical Achievement Award 2016 - Watson Conversation Service
  11. Invention Achievement Awards

Selected Patents

Complete list on Google Patents

  1. US Patent 10937416 Cross-domain multi-task learning for text classification
  2. US Patent 10977445 Weighting features for an intent classification system
  3. US Patent 11023683 Out-of-domain sentence detection
  4. US Patent 11093707 Adversarial training data augmentation data for text classifiers
  5. US Patent 11120225 Updating an online multi-domain sentence representation generation module of a text classification system
  6. US Patent 11068656 Displaying text classification anomalies predicted by a text classification model

Selected Publications

Complete list on Google Scholar

Blog and News


Under the hood: all the natural language understanding technology that makes Watson Assistant powerful

All the natural language understanding technology that makes Watson Assistant so powerful.

Medium | May 26, 2021

5 reasons NLP for chatbots improves performance

Natural language processing takes chatbots from order takers to true conversational agents. Find out how NLP for chatbots advances interaction.

TechTarget | Apr 19, 2021

AI Lifecycle for Virtual Assistants

While deploying virtual assistants it is important to focus on building conversational experiences which work seamlessly.

Medium | Apr 23, 2021

Watson Assistant improves intent detection accuracy, leads against AI vendors cited in published study

Watson Assistant has a new and improved intent detection algorithm, which is more accurate versus commercial and open-source solutions.

IBM Watson Blog | Dec 10, 2020

Announcing nominees for the second annual Women in AI Awards

Rising Star Nominee

VentureBeat | Jul 15, 2020

Why Zero-Effort Irrelevance is Relevant

How We Designed the New Zero-Effort Irrelevant Question Detection Feature in Watson Assistant

Medium | Nov 14, 2019

A New State-of-the-Art Method for Relation Extraction

IBM Research AI and IBM Watson worked together to develop a promising method that achieves state-of-the-art performance on relation extraction.

IBM Research Blog | Jul 29, 2019