Saloni Potdar

Senior AI/ML Manager @ Apple

I am a Senior Applied Research Manager with 8 years of management experience and over 10 years of industry experience. I work in the Siri and Search team at Apple where I work on building Apple Intelligence AI features that powers natural interactions across Siri, Spotlight and Safari. My research interests lie at the intersection of Generative AI, Question Answering, Dialog Systems and Knowledge Graphs. I have 30+ patents and 20+ publications with 1000+ citations in top tier research conferences like ACL, NAACL, EMNLP, AAAI, etc.


Education

M.S. in Intelligent Information Systems
Carnegie Mellon University, Pittsburgh, USA
Advisor: Jamie Callan
B.E. in Computer Engineering
University of Pune, Pune, India

Work Experience

Oct 2022 - Present
Apple Inc., Seattle, WA, USA
Senior AI/ML Manager, Question Answering
Lead the applied research team for Knowledge Graph Machine Learning where we build features that powers interactions across Siri, Safari and Spotlight Search. I currently work on Question Answering, Semantic Annotation, Entity Linking and Knowledge Graphs.
Feb 2015 - Sep 2022
IBM Watson, New York, NY, USA
Senior Staff Applied Scientist and Engineering Manager, Watson Assitant
Manager and lead for the applied research team that designed and developed algorithms for IBM's conversational AI product - Watson Assistant. I worked on the Natural Language Understanding components of Waston Assistant which includes intent classification, entity recognition, spellcheck and irrelevant detection across multiple 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.
May 2014 - Aug 2014
IBM Watson, Cambridge, MA, USA
Applied Research Intern, Watson Core Algorithms
My work revolved around using Distributional Semantics to improve the Watson Question Answering system. We used query expansion, synonym generation and question classification to improve the Watson Question Answering system.
2012 - 2013
Tata Consultancy Services, Pune, India
Assistant System Engineer,

Selected Honors and Awards

2024
Outstanding Paper Award at EMNLP 2024
Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs
2023
Women in AI Awards North America
Special Jury Recognition
2022
MIT 35 Innovators under 35 - Semi Finalist
https://www.technologyreview.com/
2022
Women in AI Awards Finalist - Rising Star
VentureBeat
2022
IBM Master Inventor
Title recognizing sustained and outstanding contributions to IP
2021
IBM Corporate Award
Outstanding technical contributions to the Watson Assistant product which resulted in high business impact
2021
IBM Outstanding Technical Achievement Award
State-of-the-art algorithms for intent classification and entity recognition in Watson Assistant
2020
IBM Research AI Accomplishment (A-level)
Meta-Learning for Low-Resource NLP
2020
IBM Corporate Award
Outstanding technical contributions for language enablement for Watson Services which resulted in high business impact
2019
Women in Leadership Program
I was one of the 25 women leaders across IBM selected for the fully funded eCornell certificate program
2018
IBM Corporate Award
Outstanding technical contributions to the Watson Conversation Service product which resulted in high business impact
2018
Best of IBM Award
Awarded to less than 1000 employees globally contributions to IBM’s business
2017
IBM Eminence and Excellence Award
Awarded for exceptional contributions to IBM Watson
2016
IBM Outstanding Technical Achievement Award
Watson Conversation Service
2017, 2018, 2019, 2020, 2021, 2022
IBM Invention Achievement Awards

Publications

Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs
Simone Conia , Daniel Lee , Min Li , Umar Farooq Minhas , Saloni Potdar , Yunyao Li
EMNLP (Main Track). 2024.
PDF Outstanding Paper
AGRaME Any-Granularity Ranking with Multi-Vector Embeddings
Revanth Gangi Reddy , Omar Attia , Yunyao Li , Heng Ji , Saloni Potdar
EMNLP (Main Track). 2024.
PDF
ConvKGYarn Spinning Configurable and Scalable Conversational Knowledge Graph QA datasets with Large Language Models
Ronak Pradeep , Daniel Lee , Ali Mousavi , Jeff Pound , Yisi Sang , Jimmy Lin , Ihab Ilyas , Saloni Potdar , Mostafa Arefiyan , Yunyao Li
EMNLP (Industry Track). 2024.
PDF
Entity Disambiguation via Fusion Entity Decoding
Junxiong Wang , Ali Mousavi , Omar Attia , Saloni Potdar , Alexander Rush , Umar Farooq Minhas , Yunyao Li
NAACL (Main Track). 2024.
PDF
Do Large Language Models Have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMs
Yanzhu Guo , Simone Conia , Zelin Zhou , Min Li , Saloni Potdar , Henry Xiao
arXiv preprint. 2024.
PDF
Distinguish Sense from Nonsense Out-of-Scope Detection for Virtual Assistants
Cheng Qian , Haode Qi , Gengyu Wang , Ladislav Kunc , Saloni Potdar
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing Industry Track. 2022.
PDF
Fast and Light-Weight Answer Text Retrieval in Dialogue Systems
Hui Wan , Siva Sankalp Patel , William Murdock , Saloni Potdar , Sachindra Joshi
NAACL (Industry Track). 2022.
PDF
Benchmarking Language-agnostic Intent Classification for Virtual Assistant Platforms
Gengyu Wang , Cheng Qian , Lin Pan , Haode Qi , Ladislav Kunc , Saloni Potdar
Proceedings of the Workshop on Multilingual Information Access (MIA). 2022.
PDF
Comparing Model Development Practices in B2B vs B2C Machine Learning Teams
Navneet Rao , Saloni Potdar
Workshop on Applied Machine Learning Management - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2022.
PDF
Improved text classification via contrastive adversarial training
Lin Pan , Chung-Wei Hang , Avirup Sil , Saloni Potdar
Proceedings of the AAAI Conference on Artificial Intelligence. 2022.
PDF
Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques A Comprehensive Study
Xiangyang Mou , Chenghao Yang , Mo Yu , Bingsheng Yao , Xiaoxiao Guo , Saloni Potdar , Hui Su
Transactions of the Association for Computational Linguistics. 2021.
PDF
Benchmarking Commercial Intent Detection Services with Practice-Driven Evaluations
Haode Qi , Lin Pan , Atin Sood , Abhishek Shah , Ladislav Kunc , Mo Yu , Saloni Potdar
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies Industry Papers. 2021.
PDF
Multilingual BERT Post-Pretraining Alignment
Lin Pan , Chung-Wei Hang , Haode Qi , Abhishek Shah , Mo Yu , Saloni Potdar
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies. 2020.
PDF
Frustratingly Hard Evidence Retrieval for QA Over Books
Xiangyang Mou , Mo Yu , Bingsheng Yao , Chenghao Yang , Xiaoxiao Guo , Saloni Potdar , Hui Su
Proceedings of the 1st Joint Workshop on Narrative Understanding, Storylines, and Events. 2020.
PDF
Diverse Few-Shot Text Classification with Multiple Metrics
Mo Yu , Xiaoxiao Guo , Jinfeng Yi , Shiyu Chang , Saloni Potdar , Gerald Tesauro , Wang, Haoyu
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies. 2018.
PDF
Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers
Haoyu Wang , Ming Tan , Mo Yu , Shiyu Chang , Dakuo Wang, , Kun Xu , Xiaoxiao Guo , Saloni Potdar
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019.
PDF
Context-Aware Conversation Thread Detection in Multi-Party Chat
Ming Tan , Dakuo Wang , Yupeng Gao , Haoyu Wang , Saloni Potdar , Xiaoxiao Guo , Shiyu Chang , Mo Yu
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.
PDF
Out-of-Domain Detection for Low-Resource Text Classification Tasks
Ming Tan , Yang Yu , Haoyu Wang , Dakuo Wang , Saloni Potdar , Shiyu Chang , Mo Yu
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.
PDF
Identifying student leaders from MOOC discussion forums through language influence
Seungwhan Moon , Saloni Potdar , Lara Martin
Proceedings of the EMNLP 2014 Workshop on Analysis of Large Scale Social Interaction in MOOCs. 2014.
PDF
Neural Models for Sequence Chunking
Feifei Zhai , Saloni Potdar , Bing Xiang , Bowen Zhou
AAAI Conference on Artificial Intelligence. 2017.
PDF
Robust Task Clustering for Deep Many-Task Learning
Mo Yu , Xiaoxiao Guo , Jinfeng Yi , Shiyu Chang , Saloni Potdar , Gerald Tesauro , Wang, Haoyu , Bowen Zhou
arXiv preprint arXiv:1708.07918. 2017.
PDF

Patents

Configuring artificial intelligence-based virtual assistants using response modes
Matthew Richard Arnold , Eric Donald Wayne , Saloni Potdar
US Patent App. 18085257. 2024.
Pretraining of Split Layer Portions for Multilingual Model
Lin Pan , Haode Qi , Ladislav Kunc , Saloni Potdar
US Patent App. 18063788. 2024.
PDF
Detecting out-of-domain text data in dialog systems using artificial intelligence
Cheng Qian , Haode Qi , Saloni Potdar , Ladislav Kunc
US Patent App. 17/897,887. 2024.
PDF
Out of domain sentence detection
Haode Qi , Cheng Qian , Ladislav Kunc , Saloni Potdar , Eric Wayne
US Patent App. US17/815,630. 2024.
PDF
Conversational AI with multi-lingual human chatlogs
Haode Qi , Lin Pan , Abhishek Shah , Ladislav Kunc , Saloni Potdar
US Patent 11,853,712. 2023.
PDF
Out-of-domain encoder training
Ming Tan , Dakuo Wang , Mo Yu , Haoyu Wang , Yang Yu , Shiyu Chang , Saloni Potdar
US Patent 11,645,514. 2023.
PDF
Domain specific model compression
Haoyu Wang , Yang Yu , Ming Tan , Saloni Potdar
US Patent 11,620,435. 2023.
PDF
Artificial intelligence based context dependent spellchecking
Panos Karagiannis , Ladislav Kunc , Saloni Potdar , Haoyu Wang , Navneet Rao
US Patent 11,301,626. 2022.
PDF
Intent classification distribution calibration
Haoyu Wang , Ming Tan , Dakuo Wang , Chuang Gan , Saloni Potdar
US Patent 11,436,528. 2022.
PDF
Contextual question answering using human chat logs
Yang Yu; , Ming Tan , Shasha Lin , Saloni Potdar
US Patent 11,443,117. 2022.
PDF
Routing text classifications within a cross-domain conversational service
Ming Tan , Ladislav Kunc , Yang Yu; , Haoyu Wang , Saloni Potdar
US Patent 11,270,077. 2022.
PDF
Evaluating text classification anomalies predicted by a text classification model
Ming Tan , Saloni Potdar , Lakshminarayanan Krishnamurthy
US Patent 11,537,821. 2022.
PDF
Hybrid model for short text classification with imbalanced data
Yang Yu , Ming Tan , Ravi Nair , Haoyu Wang , Saloni Potdar
US Patent 11,328,221. 2022.
PDF
Unintended bias detection in conversational agent platforms with machine learning model
Navneet Rao , Ming Tan , Haode Qi , Yang Yu , Panos Karagiannis , Saloni Potdar
Google Patents. 2022.
Generating question answer pairs
Dakuo Wang , Mo Yu , Chuang Gan , Saloni Potdar
US Patent App. 17/302,550. 2022.
PDF
Intent Classification using non-correlated features
Abhishek Shah , Ladislav Kunc , Haode Qi , Lin Pan , Saloni Potdar
US Patent App. 17/350,116. 2024.
PDF
Weak supervised abnormal entity detection
Haode Qi , Ming Tan , Yang Yu , Navneet Rao , Ladislav Kunc , Saloni Potdar
US Patent 11,423,227. 2022.
PDF
Intent boundary segmentation for multi-intent utterances
Ming Tan , Haoyu Wang , Saloni Potdar , Yang Yu , Navneet Rao , Haode Qi
US Patent 11,308,944. 2022.
PDF
Mechanisms for continuous improvement of automated machine learning
Haode Qi , Ming Tan , Ladislav Kunc , Saloni Potdar
US Patent 11,423,333. 2022.
PDF
Feature reweighting in text classifier generation using unlabeled data
Yang Yu , Haode Qi , Haoyu Wang , Ming Tan , Navneet Rao , Saloni Potdar Robert Yates
US Patent 11,216,619. 2022.
PDF
Suggestion of new entity types with discriminative term importance analysis
Haode Qi , Ming Tan , Yang Yu , Navneet Rao , Saloni Potdar , Haoyu Wang
US Patent 11,379,666. 2022.
PDF
Learning Parameter Sampling Configuration for Automated Machine Learning
Haode Qi , Ming Tan , Ladislav Kunc , Saloni Potdar
Google Patents. 2021.
PDF
Privacy Protection Through Template Embedding
Haode Qi , Saloni Potdar , Ming Tan , Navneet Rao
Google Patents. 2021.
PDF
Bias Detection in Conversational Agent Platforms
Navneet Rao , Ming Tan , Haode Qi , Yang Yu , Panos Karagiannis , Saloni Potdar
Google Patents. 2021.
PDF
Adversarial training data augmentation data for text classifiers
Ming Tan , Ruijian Wang , Inkit Padhi , Saloni Potdar
US Patent 11,093,707. 2021.
PDF
Displaying text classification anomalies predicted by a text classification model
Ming Tan , Saloni Potdar , Lakshminarayanan Krishnamurthy
US Patent 11,068,656. 2021.
PDF
Updating an online multi-domain sentence representation generation module of a text classification system
Ming Tan , Ladislav Kunc , Yang Yu , Haoyu Wang , Saloni Potdar
US Patent 11,120,225. 2021.
PDF
Cross-domain multi-task learning for text classification
Ming Tan , Haoyu Wang , Ladislav Kunc , Yang Yu , Saloni Potdar
US Patent 10,937,416. 2021.
PDF
Displaying text classification anomalies predicted by a text classification model
Ming Tan , Saloni Potdar , Lakshminarayanan Krishnamurthy
US Patent 11,074,414. 2021.
PDF
Weighting features for an intent classification system
Yang Yu , Ladislav Kunc , Haoyu Wang , Ming Tan , Saloni Potdar
US Patent 10,977,445. 2021.
PDF
Out-of-domain sentence detection
Inkit Padhi , Ruijian Wang , Haoyu Wang , Saloni Potdar
US Patent 11,023,683. 2021.
PDF
Adversarial training data augmentation for generating related responses
Ming Tan , Ruijian Wang , Inkit Padhi , Saloni Potdar
US Patent 11,189,269. 2021.
PDF
Implementing dynamic confidence rescaling with modularity in automatic user intent detection systems
Yang Yu , Ladislav Kunc , Saloni Potdar
Google Patents. 2020.
PDF

Services

Apple Ph.D. Fellowship Selection Committee (Information Retrieval and Knowledge Graph) 2023, 2024
Apple Internal AIML Conference (Knowledge Bases and Search Track Chair) 2022, 2023, 2024
ACL/NAACL/EMNLP ARR (Area Chair) 2024
EMNLP Industry Track (Area Chair) 2024
NAACL Industry Track (Reviewer) 2024
WAMLM KDD (Co-organizer) 2024
WAMLM KDD (Co-organizer) 2023
EMNLP Industry Track (Reviewer) 2023
ACL Industry Track (Reviewer) 2023
Web Conference Industry Track (Reviewer) 2023
EMNLP Industry Track (Reviewer) 2022
NAACL Industry Track (Reviewer) 2022
ACL/NAACL/EMNLP ARR (Reviewer) 2021
AAAI (Reviewer) 2021
Workshop for Women in Machine Learning 2019 (Reviewer) 2019
CCL (Reviewer) 2017

Collaborators and Interns

Jun 2023 - present
Revanth Gangi Reddy at Apple
PhD, University of Illinois Urbana-Champaign
Jan 2023 - present
Simone Conia at Apple
PhD, Sapienza NLP
Jun 2023 - present
Ronak Pradeep at Apple
PhD, University of Waterloo
Feb 2023 - present
Daniel Lee at Apple
Bachelor, University of Calgary
Jul 2023 - present
Charlie (Zelin) Zhou at Apple
Masters, Shanghai Jiao Tong University
Jun 2023 - Dec 2023
Junxiong Wang at Apple
PhD, Cornell University
Summer 2021
George Karagiannis at IBM
PhD, Cornell University
Summer 2020
Chenghao Yang at IBM
PhD, University of Chicago

Articles and Blogs

Oct 2024

Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs

Apple Machine Learning Research
Oct 2024

ConvKGYarn Spinning Configurable and Scalable Conversational Knowledge Graph QA Datasets with Large Language Models

Apple Machine Learning Research
Aug 2024

Spinning Configurable and Scalable Conversational Knowledge Graph QA Datasets with Large Language Models

Apple Machine Learning Research
Jun 2024

AGRaME Any Granularity Ranking with Multi-Vector Embeddings

Apple Machine Learning Research
Aug 2024

Entity Disambiguation via Fusion Entity Decoding

Apple Machine Learning Research
May 26 2021

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

Medium - All the natural language understanding technology that makes Watson Assistant so powerful.
Apr 23 2021

AI Lifecycle for Virtual Assistants

Medium- While deploying virtual assistants it is important to focus on building conversational experiences which work seamlessly.
Nov 14 2019

Why Zero-Effort Irrelevance is Relevant

Medium - How We Designed the New Zero-Effort Irrelevant Question Detection Feature in Watson Assistant
Jul 29 2019

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

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

Press

Aug 17 2023

Finalists and Special Jury Recognitions announced for Women in AI Awards North America 2023

Women in AI - Special Jury Award
Jul 10 2022

Putting more knowledge at the fingertips of non-English speakers

PrimeQA for non-english speakers
July 8 2022

Meet the nominees for the 2022 VentureBeat Women in AI Awards

VentureBeat - Rising Star Nominee
Apr 19 2021

5 reasons NLP for chatbots improves performance

TechTarget - Natural language processing takes chatbots from order takers to true conversational agents. Find out how NLP for chatbots advances interaction.
Dec 10 2020

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

IBM - Watson Assistant has a new and improved intent detection algorithm, which is more accurate versus commercial and open-source solutions.
Jul 15 2020

Announcing nominees for the second annual Women in AI Awards

VentureBeat - Rising Star Nominee