Skip to content
PGPawan GoyalCSE · IIT Kharagpur
Portrait of Pawan Goyal
Professor · Computer Science & Engineering

Pawan Goyal

Indian Institute of Technology Kharagpur, India — 721302

I work on Natural Language Processing, Text Mining, Information Retrieval and Sanskrit Computational Linguistics, member of the CNeRG research group and lead the Sanganaka research group.

Google Scholar CV

Office: +91-3222-282370

204+publications
13years at IIT Kharagpur
2NPTEL courses
17PhDs supervised
About

Brief bio

I joined the Department of Computer Science and Engineering, Indian Institute of Technology, Kharagpur as an Assistant Professor on July 30th, 2013. Prior to that, I was working at INRIA Paris-Rocquencourt as a post doctoral fellow with Prof. Gérard Huet on The Sanskrit Heritage Site.

I did my B. Tech. in Electrical Engineering from Indian Institute of Technology, Kanpur. I received my Ph. D. from the Intelligent Systems Research Centre, Faculty of Computing and Engineering, University of Ulster, UK. My PhD advisors were Prof. Laxmidhar Behera and Prof. T. M. McGinnity. The topic of my PhD dissertation was “Analytic Knowledge Discovery Techniques for Ad-Hoc Information Retrieval and Text Summarization”.

Research interests

Natural Language Processing Sanskrit Computational Linguistics Information Retrieval Text Mining & Summarization Legal NLP AI for Materials
Highlights NPTEL · Free online

Watch the lectures

Natural Language Processing and Deep Learning for NLP — full video playlists.

 Research group

Sanganaka Lab

Our group working on Sanskrit computational linguistics and NLP.

 People

Students & alumni

Current PhD and MS scholars, and where our graduates are now.
Gallery

Moments

Talks, workshops and conferences with the group.

Chennai · March 2026With Sairam Surenderasan on the evolving impact of AI on learning at the 14th ThinkEdu Conclave.
BAIR · April 2023Visit to Berkeley Artificial Intelligence Research.
Summer School · Jun 2026At the First Summer School on Sanskrit Computational Linguistics, organised by the Centre for Digital Humanities, MAHE Bengaluru with IIT Kharagpur.
RecognitionBeing honoured for WSC.
ConferencePoster session with students.
Updates

News

  1. Our papers, "InLegalLaySum: A Novel Benchmark for Lay Summarization of Indian Legal Documents" and "PINGALA: Prosody-Aware Decoding for Sanskrit Poetry Generation" got accepted in AACL-Findings'26.

  2. Our paper, "Mitrasaṃgraha: A Comprehensive Classical Sanskrit Machine Translation Dataset" got accepted in WMT'26 (The tenth conference on Machine Translation).

  3. Our papers, "DiffNeCTIS: Diffusion-based Nested Compound Type Identification for Sanskrit" and "Padamitra: Grounded Glossary Generation for Classical Sanskrit" got accepted in EMNLP'26.

  4. Our paper, "Lightweight Cross-Lingual Speaker Adaptation for Indic TTS" got accepted in Interspeech'26.

  5. Our paper, "Model Agnostic Graph Prompt Learning for Crystal Property Prediction" got accepted in UAI'26.

  6. Our paper, "Latent Diffusion Pretraining for Crystal Property Prediction" got accepted in ICML'26.

  7. Our paper, "DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion" got accepted in SIGIR'26 (Full Paper).

  8. Our paper, "Router-Suggest: A Router-based Framework for Auto-Completions in Visually-Grounded Conversations" got accepted in EACL'26 Industry Track.

  9. 2 main papers and one findings got accepted in EACL'26.

  10. Our AAAI 2022 paper, "LeSICiN: A Heterogeneous Graph-Based Approach for Automatic Legal Statute Identification from Indian Legal Documents" has won the Markose Thomas Memorial Award for being one of the two best research papers published from the Department of CSE, IIT Kharagpur during 2022-23.

  11. Our paper, "From Meters to Meaning: Untangling the Sanskrit Verses" got accepted in AACL-IJCNLP'25.

  12. Our paper, "LLM Meets Diffusion: A Hybrid Framework for Crystal Material Generation" got accepted in NeurIPS'25.

  13. 6 main papers and a Finding paper got accepted in EMNLP'25.

  14. Our paper, "ReFeR: Improving Evaluation and Reasoning through Hierarchy of Models" got accepted in TMLR.

  15. Our paper, "Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classification" got accepted in ACL Findings'25.

  16. Our paper, "Periodic Materials Generation using Text-Guided Joint Diffusion Model" got accepted in ICLR'25.

  17. I will be offering a new course on NPTEL, "Deep Learning for Natural Language Processing". Course Website

  18. 3 main papers and a Finding paper got accepted in EMNLP'24.

  19. Abhilash Nandy received the Microsoft Research India PhD Award.

  20. Our paper, "FastDoc: Domain-Specific Fast Continual Pre-training Technique using Document-Level Metadata and Taxonomy" got accepted in TMLR.

  21. Our papers, "IL-TUR: Benchmark for Indian Legal Text Understanding and Reasoning" (long paper, main) and "On The Persona-based Summarization of Domain-Specific Documents" (short paper, Findings) got accepted in ACL'24.

  22. Our papers, "Instruction-Guided Bullet Point Summarization of Long Financial Earnings Call Transcripts" (short paper) and "Legal Statute Identification: A Case Study using State-of-the-Art Datasets and Methods" (Resource and Reproducibility track) got accepted in SIGIR'24.

  23. Our papers, "Parameter-Efficient Instruction Tuning of Large Language Models For Extreme Financial Numeral Labelling" and "Order-Based Pre-training Strategies for Procedural Text Understanding" got accepted in NAACL'24 (main conference).

  24. Our paper, "How Robust are the QA Models for Hybrid Scientific Tabular Data? A Study using Customized Dataset" got accepted in LREC-Coling'24 (short).

  25. 4 long papers accepted in EMNLP'23 (Findings).

  26. Our proposal, "A Human-Aligned Automated Evaluation Framework for Natural Language Generation via Large Language Models" got selected for the Microsoft Accelerate Foundation Models Research Program.

  27. I will be serving as an area chair for EMNLP'23.

  28. I will be serving as PC co-chair for IndoML'23 in IIT Bombay along with Prof. Abir De and Prof. Sunita Sarawagi.

  29. I will be serving as PC co-chair for Big Data Analytics (BDA)'23 in IIIT Delhi along with Prof. Sourav Bhowmick, NTU.

  30. Our paper, "SanskritShala: A Neural Sanskrit NLP Toolkit with Web-Based Interface for Pedagogical and Annotation Purposes" got accepted in ACL'23 (System Demonstrations).

  31. Our paper, "CrysMMNet: Multimodal Representation for Crystal Property Prediction" got accepted in UAI'23.

  32. Our paper, "Financial Numeric Extreme Labelling: A dataset and benchmarking" got accepted in Findings of ACL'23 (short).

  33. Our papers, "Intent Identification and Entity Extraction for Healthcare Queries in Indic Languages" (Long paper, findings) and "Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing" (Short paper, main) got accepted in EACL'23.

  34. Our paper, "CrysGNN : Distilling pre-trained knowledge to enhance property prediction for crystalline materials" got accepted in AAAI'23.

  35. Our papers, "TransLIST: A Transformer-Based Linguistically Informed Sanskrit Tokenizer" (Long paper, findings) and "ECTSum: A New Benchmark Dataset for Bullet Point Summarization of Long Earnings Call Transcripts" (Long paper, main) got accepted in EMNLP'22.

  36. Our papers, "Legal Case Document Summarization: Extractive and Abstractive Methods and their Evaluation" (Long paper, main) and "ArgGen: Prompting Text Generation Models for Document-Level Event-Argument Aggregation" (short paper, findings) got accepted in AACL'22.

  37. Our papers, "A Novel Multi-Task Learning Approach for Context-Sensitive Compound Type Identification in Sanskrit" (Long paper, Oral presentation) and "Does Meta-learning Help mBERT for Few-shot Question Generation in a Cross-lingual Transfer Setting for Indic Languages?" (Short paper, poster presentation) got accepted in Coling'22.

  38. Received Faculty Excellence Award (Associate Level) from IIT Kharagpur.

  39. Our paper, "Linguistically Informed Post-processing for ASR Error correction in Sanskrit" got accepted in Interspeech.

  40. Our proposal, " Adapting Dialog Systems to New Domains through Natural Language Interactions" got selected as part of Microsoft Academic Partnership Grant (MAPG 2022) program.

  41. Our papers, "Representation Learning for Conversational Data using Discourse Mutual Information Maximization" and "A Framework to Generate High-quality Datapoints for Multiple Novel Intent Detection" got accepted in NAACL'22 (main and findings, respectively).

  42. Our paper, "Using Data Augmentation to Identify Relevant Reviews for Product Question Answering" got accepted in the Web Conference as a poster.

  43. Our paper, "CrysXPP: An Explainable Property Predictor for Crystalline Materials" got accepted in npj Computational Materials.

  44. Our paper, "LeSICiN: A Heterogeneous Graph-based Approach for Automatic Legal Statute Identification from Indian Legal Documents" got accepted in AAAI'22.

  45. Our paper, "MTLVS: A Multi-Task Framework to Verify and Summarize Crisis-Related Microblogs" got accepted in WSDM'22.

  46. Our paper, "Network Embeddings from Distributional Thesauri for Improving Static Word Representations" got accepted in Expert Systems with Applications.

  47. Our paper received Hypertext Ted Nelson Best Newcomer Paper Award.

  48. Our papers, "PASTE: A Tagging-free Decoding Framework using Pointer Networks for Aspect Sentiment Triplet Extraction" and "Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA" got accepted in EMNLP'21 (main and findings, respectively).

  49. Our proposal, " Multilingual Dialogue as a Novel Framework for AutoSuggest" got selected as part of Microsoft Academic Partnership Grant 2021 program.

  50. Our paper, " Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights" got accepted in Findings of ACL'21.

  51. Our paper, " Hierarchical Transformer for Task Oriented Dialog Systems" got accepted in NAACL-HLT'21.

  52. Our paper, " MatScIE: An automated tool for the generation of databases of methods and parameters used in the computational materials science literature" got accepted in Computational Materials Science, Elsevier.

  53. Abhilash Nandy and Ankan Mullick receive Prime Minister's Research Fellowship (PMRF).

  54. One Full paper and One Reproducibility Track paper got accepted in ECIR'21.

  55. Our paper, "HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection" got accepted in AAAI'21.

  56. Our paper, "A Graph Based Framework for Structured Prediction Tasks in Sanskrit" got accepted in Computational Linguistics Journal.

  57. Our paper, "Automatic Crime Identification from Facts: A Few Sentence-Level Crime Annotations is All You Need" got accepted in COLING.

  58. Our paper, "Keep it Surprisingly Simple: A Simple First Order Graph Based Parsing Model for Joint Morphosyntactic Parsing in Sanskrit" got accepted in EMNLP as a short paper.

  59. Received INAE Young Engineer Awards 2020.

  60. Our paper, "Hate begets Hate: A Temporal Study of Hate Speech" got accepted in ACM CSCW.

  61. Received Google India AI/ML Research Awards 2020.

  62. Our paper, "Read what you need: Controllable Aspect-based Opinion Summarization of Tourist Reviews" got accepted in SIGIR 2020 as a short paper.

  63. Our paper, "Logic Constrained Pointer Networks for Interpretable Textual Similarity" got accepted in IJCAI 2020.

  64. Our paper, "Aspect-based Sentiment Analysis of Scientific Reviews" got accepted in JCDL 2020.

  65. Two papers got accepted in LREC 2020.

  66. Our paper, "Incorporating Domain Knowledge into Medical NLI using Knowledge Graphs" got accepted in EMNLP 2019 as a short paper.

  67. Our paper, "Spread of hate speech in online social media" got the best paper award (honorable mention) at WebSci 2019.

  68. Our long paper, "On the Compositionality Prediction of Noun Phrases using Poincaré embeddings" and a short paper, "Poetry to Prose Conversion in Sanskrit as a Linearisation Task: A case for Low-Resource Languages" got accepted in ACL 2019.

  69. Our paper, "Addressing Vocabulary Gap in E-commerce Search" got accepted in SIGIR 2019 as a short paper.

  70. Our paper, "Spread of hate speech in online social media" got accepted in WebSci 2019.

  71. Our paper, "Thou shalt not hate: Countering online hate speech" got accepted in ICWSM 2019.

  72. One long paper, "Automated Early Leaderboard Generation From Comparative Tables" and three short papers got accepted in ECIR 2019.

  73. Our paper, "Free as in Free Word Order: An Energy Based Model for Word Segmentation and Morphological Tagging in Sanskrit" got accepted in EMNLP.

  74. Our paper, "Opinion Conflicts: An Effective Route to Detect Incivility in Twitter" got accepted in CSCW.

  75. Our paper, "Upcycle Your OCR: Reusing OCRs for Post-OCR Text Correction in Romanised Sanskrit" got accepted in CoNLL.

  76. Our paper, "WikiRef: Wikilinks as a route to recommending appropriate references for scientific Wikipedia pages" got accepted in Coling.

  77. Our paper, "Identifying Sub-events and Summarizing Information during Disasters" got accepted in SIGIR.

  78. Our paper, "Can Network Embedding of Distributional Thesaurus be Combined with Word Vectors for Better Representation?" got accepted in NAACL-HLT.

  79. Our paper, "Extracting and Summarizing Situational Information from the Twitter Social Media during Disasters" got accepted in ACM Transactions on the Web.

  80. Two full papers, "Building a Word Segmenter for Sanskrit Overnight" and "Network Features Based Co-hyponymy Detection" got accepted in LREC 2018 for oral presentations.

  81. Our Paper, "Automated Assistance in E-commerce: An Approach based on Category-Sensitive Retrieval" got accepted in ECIR 2018 as a short paper.

  82. I will be chairing the Young Researchers' Symposium at CODS-COMAD 2018 along with Dr. Amit Awekar from IIT Guwahati. Please consider submitting. You can find more details here.

  83. Our Paper, "Extracting Entities of Interest from Comparative Product Reviews" got accepted in CIKM 2017 as a short paper.

  84. We are organizing ACM summer school on NLP and Machine Learning from June 1st to June 21st, 2017. More details can be found here.

  85. Our Paper, "Relay-Linking Models for Prominence and Obsolescence in Evolving Networks" got accepted in KDD 2017 for a poster presentation.

  86. Two full papers, "Understanding the Impact of Early Citers on Long-Term Scientific Impact", "WikiM: Metapaths based Wikification of Scientific Abstracts" and one short paper, "Citation sentence reuse behavior of scientists: A case study on massive bibliographic text dataset of computer science" accepted in JCDL 2017.

  87. We are organizing workshop on Complex and Social Networks on March 15th, 2017 in Gargi Auditorium. Prof. Frank Schweitzer (ETH, Zurich), Prof. Laxmidhar Behera (IIT Kanpur) and Dr. Manish Gupta (Microsoft Bing) are the speakers. There will also be a panel discussion on "How to sell your thesis to industry". For more details, visit the website here.

  88. OCR++ got selected for the Gandhian Young Technological Innovation (GYTI) Award/Appreciation 2017.

  89. Our paper, "A Generic Opinion-Fact Classifier with Application in Understanding Opinionatedness in Various News Section" got accepted as a poster in WWW 2017.

  90. Our papers, "Word Segmentation in Sanskrit Using Path Constrained Random Walks" and "OCR++: A Robust Framework For Information Extraction from Scholarly Articles" got accepted in Coling 2016.

  91. Our paper, "peq : An explainable, specification-based, aspect-oriented product comparator for e-commerce" got accepted in ACM CIKM, 2016 as a short paper.

  92. Our paper, "Summarizing Situational Tweets in Crisis Scenario" got accepted in ACM HyperText, 2016.

  93. Our paper, "FeRoSA: A Faceted Recommendation System for Scientific Articles" got accepted in PAKDD, 2016.

  94. Our papers, "Extracting Situational Information from Microblogs during Disaster Events: A Classification-Summarization Approach" and "The role of citation context in predicting long-term citation profiles: an experimental study based on a massive bibliographic text dataset" got accepted in ACM CIKM, 2015.

  95. Our paper, "On the formation of circles in co-authorship networks" got accepted in ACM SIGKDD, 2015.

  96. Our paper, "An automatic approach to identify word sense changes in text media across timescales" got accepted in JNLE special issue on Graph Methods for NLP.

  97. Our paper, "On the categorization of scientific citation profiles in computer sciences" got accepted in Communications of the ACM.

  98. Our proposal, "IndicView: because language is no more a barrier" has been accepted as part of the Google - IIT Pilot program.

  99. Received a grant of USD 1000 from Yahoo! Labs towards encouraging student participation in the SNLP course projects this semester.

Service

Professional activities

  • Senior Area Chair: EMNLP 2026, ACL 2026, EMNLP 2025, AACL-IJCNL 2025, EMNLP 2024
  • Academic Co-ordinator for the ACM India Summer School on Generative AI for Text at IIT Gandhinagar from June 24th - July 5th, 2024.
  • Academic Co-ordinator for the First Summer School on Sanskrit Computational Linguistics at MAHE Bengaluru from June 22nd - 27th, 2026.
  • PC Chair: ISCLS 2026, BDA 2023, IndoML 2023
  • We organized sixth international conference on Sanskrit Computational Linguistics from October 23-25, 2019 at IIT Kharagpur. For more details, please visit this link.
  • Senior PC / Meta-Reviewer / Area Chair: AAAI 2027, EMNLP 2023, AAAI 2023, AAAI 2021