Puneet Agrawal
Puneet Agrawal has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Manish Gupta
Microsoft Corporation, Hyderabad, India
6 shared publications - Kedhar Nath Narahari
Microsoft
3 shared publications - Ankush Chatterjee
Microsoft
2 shared publications - Kaushal Kumar Maurya
MBZUAI
2 shared publications - Maunendra Sankar Desarkar
IIT Hyderabad, Hyderabad, India
2 shared publications - Meghana Joshi
Microsoft
2 shared publications
Latest Publications
- 2 January 2026
- Published by Springer Nature
- p. 1-11
Assessing Performance of Large Language Models in Generating Local and Trending Query Auto-completions
- 2 January 2026
- Published by Springer Nature
- p. 1-11
Assessing Performance of Large Language Models in Generating Local and Trending Query Auto-completions
- Open Access
Trie-NLG: Trie Context Augmentation to Improve Personalized Query Auto-Completion for Short and Unseen Prefixes
Query auto-completion (QAC) aims to suggest plausible completions for a given query prefix. Traditionally, QAC systems have leveraged tries curated from historical query logs to suggest most popular completions. In this context, there are two specific scenarios that are difficult to handle for any QAC system: short prefixes (which are inherently ambiguous) and unseen prefixes. Recently, personalized Natural Language Generation (NLG) models have been proposed to leverage previous session queries as context for addressing these two challenges. However, such NLG models suffer from two drawbacks: (1) some of the previous session queries could be noisy and irrelevant to the user intent for the current prefix, and (2) NLG models cannot directly incorporate historical query popularity. This motivates us to propose a novel NLG model for QAC, Trie-NLG, which jointly leverages popularity signals from trie and personalization signals from previous session queries. We train the Trie-NLG model by augmenting the prefix with rich context comprising of recent session queries and top trie completions. This simple modeling approach overcomes the limitations of trie-based and NLG-based approaches and leads to state-of-the-art performance. We evaluate the Trie-NLG model using two large QAC datasets. On average, our model achieves huge ~57% and ~14% boost in MRR over the popular trie-based lookup and the strong BART-based baseline methods, respectively. We make our code publicly available.
Open AccessTrie-NLG: Trie Context Augmentation to Improve Personalized Query Auto-Completion for Short and Unseen Prefixes
Query auto-completion (QAC) aims to suggest plausible completions for a given query prefix. Traditionally, QAC systems have leveraged tries curated from historical query logs to suggest most popular completions. In this context, there are two specific scenarios that are difficult to handle for any QAC system: short prefixes (which are inherently ambiguous) and unseen prefixes. Recently, personalized Natural Language Generation (NLG) models have been proposed to leverage previous session queries as context for addressing these two challenges. However, such NLG models suffer from two drawbacks: (1) some of the previous session queries could be noisy and irrelevant to the user intent for the current prefix, and (2) NLG models cannot directly incorporate historical query popularity. This motivates us to propose a novel NLG model for QAC, Trie-NLG, which jointly leverages popularity signals from trie and personalization signals from previous session queries. We train the Trie-NLG model by augmenting the prefix with rich context comprising of recent session queries and top trie completions. This simple modeling approach overcomes the limitations of trie-based and NLG-based approaches and leads to state-of-the-art performance. We evaluate the Trie-NLG model using two large QAC datasets. On average, our model achieves huge ~57% and ~14% boost in MRR over the popular trie-based lookup and the strong BART-based baseline methods, respectively. We make our code publicly available.
- 7 August 2023
- Published by Springer Nature in Data Mining and Knowledge Discovery
- Vol. 37 (6) , 2306-2329
trie-nlg: trie context augmentation to improve personalized query auto-completion for short and unseen prefixes
- 7 August 2023
- Published by Springer Nature in Data Mining and Knowledge Discovery
- Vol. 37 (6) , 2306-2329
trie-nlg: trie context augmentation to improve personalized query auto-completion for short and unseen prefixes
- 8 April 2022
- Published by Springer Nature
- p. 413-424
Query-Document Topic Mismatch Detection
- 6 May 2020
- Published by Springer Nature
- Vol. 12084, 235-248
Optimized Transformer Models for FAQ Answering
Informational chatbots provide a highly effective medium for improving operational efficiency in answering customer queries for any enterprise. Chatbots are also preferred by users/customers since unlike other alternatives like calling customer care or browsing over FAQ pages, chatbots provide instant responses, are easy to use, are less invasive and are always available. In this paper, we discuss the problem of FAQ answering which is central to designing a retrieval-based informational chatbot. Given a set of FAQ pages s for an enterprise, and a user query, we need to find the best matching question-answer pairs from s. Building such a semantic ranking system that works well across domains for large QA databases with low runtime and model size is challenging. Previous work based on feature engineering or recurrent neural models either provides low accuracy or incurs high runtime costs. We experiment with multiple transformer based deep learning models, and also propose a novel MT-DNN (Multi-task Deep Neural Network)-based architecture, which we call Masked MT-DNN (or MMT-DNN). MMT-DNN significantly outperforms other state-of-the-art transformer models for the FAQ answering task. Further, we propose an improved knowledge distillation component to achieve \(\sim \)2.4x reduction in model-size and \(\sim \)7x reduction in runtime while maintaining similar accuracy. On a small benchmark dataset from SemEval 2017 CQA Task 3, we show that our approach provides an NDCG@1 of 83.1. On another large dataset of \(\sim \)281K instances corresponding to \(\sim \)30K queries from diverse domains, our distilled 174 MB model provides an NDCG@1 of 75.08 with a CPU runtime of mere 31 ms establishing a new state-of-the-art for FAQ answering.- 6 May 2020
- Published by Springer Nature
- Vol. 12084, 235-248
Optimized Transformer Models for FAQ Answering
Informational chatbots provide a highly effective medium for improving operational efficiency in answering customer queries for any enterprise. Chatbots are also preferred by users/customers since unlike other alternatives like calling customer care or browsing over FAQ pages, chatbots provide instant responses, are easy to use, are less invasive and are always available. In this paper, we discuss the problem of FAQ answering which is central to designing a retrieval-based informational chatbot. Given a set of FAQ pages s for an enterprise, and a user query, we need to find the best matching question-answer pairs from s. Building such a semantic ranking system that works well across domains for large QA databases with low runtime and model size is challenging. Previous work based on feature engineering or recurrent neural models either provides low accuracy or incurs high runtime costs. We experiment with multiple transformer based deep learning models, and also propose a novel MT-DNN (Multi-task Deep Neural Network)-based architecture, which we call Masked MT-DNN (or MMT-DNN). MMT-DNN significantly outperforms other state-of-the-art transformer models for the FAQ answering task. Further, we propose an improved knowledge distillation component to achieve \(\sim \)2.4x reduction in model-size and \(\sim \)7x reduction in runtime while maintaining similar accuracy. On a small benchmark dataset from SemEval 2017 CQA Task 3, we show that our approach provides an NDCG@1 of 83.1. On another large dataset of \(\sim \)281K instances corresponding to \(\sim \)30K queries from diverse domains, our distilled 174 MB model provides an NDCG@1 of 75.08 with a CPU runtime of mere 31 ms establishing a new state-of-the-art for FAQ answering.- Open Access
A Sentiment-and-Semantics-Based Approach for Emotion Detection in Textual Conversations
Emotions are physiological states generated in humans in reaction to internal or external events. They are complex and studied across numerous fields including computer science. As humans, on reading "Why don't you ever text me!" we can either interpret it as a sad or angry emotion and the same ambiguity exists for machines. Lack of facial expressions and voice modulations make detecting emotions from text a challenging problem. However, as humans increasingly communicate using text messaging applications, and digital agents gain popularity in our society, it is essential that these digital agents are emotion aware, and respond accordingly. In this paper, we propose a novel approach to detect emotions like happy, sad or angry in textual conversations using an LSTM based Deep Learning model. Our approach consists of semi-automated techniques to gather training data for our model. We exploit advantages of semantic and sentiment based embeddings and propose a solution combining both. Our work is evaluated on real-world conversations and significantly outperforms traditional Machine Learning baselines as well as other off-the-shelf Deep Learning models.
Open AccessA Sentiment-and-Semantics-Based Approach for Emotion Detection in Textual Conversations
Emotions are physiological states generated in humans in reaction to internal or external events. They are complex and studied across numerous fields including computer science. As humans, on reading "Why don't you ever text me!" we can either interpret it as a sad or angry emotion and the same ambiguity exists for machines. Lack of facial expressions and voice modulations make detecting emotions from text a challenging problem. However, as humans increasingly communicate using text messaging applications, and digital agents gain popularity in our society, it is essential that these digital agents are emotion aware, and respond accordingly. In this paper, we propose a novel approach to detect emotions like happy, sad or angry in textual conversations using an LSTM based Deep Learning model. Our approach consists of semi-automated techniques to gather training data for our model. We exploit advantages of semantic and sentiment based embeddings and propose a solution combining both. Our work is evaluated on real-world conversations and significantly outperforms traditional Machine Learning baselines as well as other off-the-shelf Deep Learning models.