Large-Scale Text Analysis Using Generative Language Models: Discovering Public Value Expressions in AI Patents
Sergio Pelaez*, Gaurav Verma*, Barbara Ribeiro, and Philip Shapira
In Quantiative Science Studies (QSS). (* = equal contribution)
[https://direct.mit.edu/qss/article/doi/10.1162/qss_a_00285/119275] [code]
Conferences
Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space Gaurav Verma, Minje Choi, Kartik Sharma, Jamelle Watson-Daniels, Sejoon Oh, Srijan Kumar [pdf] [code] [webpage]
62nd Annual Meeting of the Association for Computational Linguistics (ACL'24)
A Community-Centric Perspective for Characterizing and Detecting Anti-Asian Violence-Provoking Speech [pdf] [webpage] Gaurav Verma, Rynaa Grover, Jiawei Zhou, Binny Mathew, Jordan Kraemer, Munmun De Choudhury, Srijan Kumar
62nd Annual Meeting of the Association for Computational Linguistics (ACL'24)
MM-SOC: Benchmarking Multimodal Large Language Models in Social Media Platforms [pdf] Yiqiao Jin, Minje Choi, Gaurav Verma, Jindong Wang, Srijan Kumar
Findings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL'24 Findings)
Better to Ask in English: Cross-Lingual Evaluation of Large Language Models for Healthcare Queries [pdf] [webpage] [code]
Yiqiao Jin*, Mohit Chandra*, Gaurav Verma, Yibo Hu, Munmun De Choudhury, Srijan Kumar (* = equal contribution)
In ACM Web Conference 2024 (ACM WWW'24)
Adversarial Text Rewriting for Text-aware Recommender Systems [pdf, code: coming soon]
Sejoon Oh, Gaurav Verma, Srijan Kumar
In ACM International Conference on Information and Knowledge Management (ACM CIKM'24)
Learning the Visualness of Text Using Large Vision-Language Models [arXiv] [webpage] Gaurav Verma, Ryan A. Rossi, Christopher Tensmeyer, Jiuxiang Gu, Ani Nenkova
In Empirical Methods in Natural Language Processing (EMNLP'23)
Cross-Modal Attribute Insertions for Assessing the Robustness of Vision-and-Language Learning [pdf] [code] Shivaen Ramshetty*, Gaurav Verma*, Srijan Kumar (* = equal contribution)
61st Annual Meeting of the Association for Computational Linguistics (ACL'23)
Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding [pdf] [code] Venkata Prabhakara Sarath Nookala*, Gaurav Verma*, Subhabrata Mukherjee, Srijan Kumar (* = equal contribution)
Findings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL'23 Findings)
Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions [pdf] [webpage] [arXiv] [code] Gaurav Verma, Vishwa Vinay, Ryan A. Rossi, Srijan Kumar
In Empirical Methods in Natural Language Processing (EMNLP'22)
Overcoming Language Disparity in Online Content Classification with Multimodal Learning Gaurav Verma, Rohit Mujumdar, Zijie Wang, Munmun De Choudhury, Srijan Kumar
In The International AAAI Conference on Web and Social Media (ICWSM'22) [pdf] [webpage] [summary video] [code & data]
Non-Linear Consumption of Videos Using a Sequence of Personalized Multimodal Fragments Gaurav Verma, Trikay Nalamada, Keerti Harpavat, Pranav Goel, Aman Mishra, Balaji Vasan Srinivasan [pdf] [video]
In ACM International Conference on Intelligent User Interfaces (ACM IUI'21)
Detecting Document Versions and Their Ordering In a Collection Natwar Modani, Anurag Maurya, Gaurav Verma, Inderjeet Jayakumar Nair, Vaidehi Patil, Anirudh Kanfade [pdf]
In International Conference on Web Information Systems Engineering (WISE'21)
[💐 Best Paper Runner-up Award]
DRAG: Director-Generator Language Modeling Framework for Non-Parallel Author Stylized Rewriting Hrituraj Singh, Gaurav Verma, Aparna Garimella, Balaji Vasan Srinivasan
In the European Chapter of the Association for Computational Linguistics (EACL'21) [arXiv] [video]
Incorporating Stylistic Lexical Preferences in Generative Language Models
Hrituraj Singh, Gaurav Verma, Balaji Vasan Srinivasan
In Empirical Methods in Natural Language Processing (EMNLP 2020): Findings.
[arXiv]
Modeling Causal Impact of Textual Style on a Target Goal Gaurav Verma, Balaji Vasan Srinivasan, Shiv Kumar Saini, Niyati Chhaya
In WWW ’20 Companion: Companion Proceedings of The Web Conference 2020
[pdf] [presentation video @WebConf 2020]
Using Image Captions and Multitask Learning for Recommending Query Reformulations Gaurav Verma, Vishwa Vinay, Sahil Bansal*, Shashank Oberoi*, Makkunda Sharma*, Prakhar Gupta (* = equal contribution)
In European Conference on Information Retrieval (ECIR'20)
[arXiv] [presentation video @ECIR]
Adapting Language Models for Non-Parallel Author-Stylized Rewriting Bakhtiyar Syed, Gaurav Verma, Balaji Vasan Srinivasan, Anandhavelu Natarajan, Vasudeva Varma
In AAAI Conference on Artificial Intelligence (AAAI'20)
[arXiv]
Learning Affective Correspondence between Music and Image Gaurav Verma, Eeshan Gunesh Dhekane, Tanaya Guha
In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'19)
[pdf] [IMAC Dataset]
Stuck? No worries!: Task-aware Command Recommendation and Proactive Help for Analysts
AM Nambhi*, Bhanu P Reddy*, AP Agarwal*, Gaurav Verma, Harvineet Singh, Iftikhar A Burhanuddin (* = equal contribution)
In ACM International Conference on User Modelling, Adaptation And Personalization (ACM UMAP'19)
[pdf] [Project page]
Workshops
Semi-Supervised Learning for Identification of Informative COVID-19 English Tweets Abhilasha Sancheti*, Kushal Chawla*, Gaurav Verma (* = equal contribution)
Proceedings of the 2020 EMNLP Workshop W-NUT: The Sixth Workshop on Noisy User-generated Text (Task 2)
[arXiv]
"To Target or Not to Target": Indentification and Analysis of Abusive Text Using Ensemble of Classifiers Gaurav Verma, Niyati Chhaya, Viswha Vinay
ICWSM'20 Safety Data Challenge
[pdf] [slides (pdf)]
Pre-prints
A Lexical, Syntactic, and Semantic Perspective for Understanding Style in Text Gaurav Verma, Balaji Vasan Srinivasan
Preprint.
[pdf] [arXiv]
Patents
Personalizing Videos with Non-Linear Playback Gaurav Verma, Trikay Nalamada, Keerti Harpavat, Pranav Goel, Aman Mishra, Balaji Vasan Srinivasan
US Patent Application 17/090,013
| Adobe Inc.
Content Fragments Aligned to Content Criteria Gaurav Verma, Suryateja BV, Samagra Sharma, Balaji Vasan Srinivasan
US Patent Application 16/809,222
| Adobe Inc.
[pdf]
Automatically Associating Context-based Sounds with Text Gaurav Verma, Vishwa Vinay, Sneha Chowdary, Siddharth Sahay, Mitansh Jain
US Patent Application 16/725,716
| Adobe Inc.
[pdf]
Goal-driven Authoring Assistance via Causal Stylistic Prescriptions Gaurav Verma, Balaji Vasan Srinivasan, Shiv Kumar Saini, Niyati Chhaya
US Patent 11,062,085
| Adobe Inc.
[pdf]
Task-aware Command Recommendations and Proactive Help Gaurav Verma, Iftikhar A Burhanuddin, Harvineet Singh, Bhanu P Reddy, AP Agarwal, AM Nambhi
US Patent Application 16/454,683
| Adobe Inc.
[pdf]
Systems for Generating Indications of Relationships between Electronic Documents Natwar Modani, Vaidehi Patil, Inderjeet Nair, Gaurav Verma, Anurag Maurya, Anirudh Kanfade
US Patent Application 17/534,744
| Adobe Inc.
Stylistic Text Rewriting for a Target Author Balaji Vasan Srinivasan, Gaurav Verma, Bakhtiyar Syed, Anandhavelu Natarajan
US Patent Application 16/800,018
| Adobe Inc.
[pdf]
Digital Document Update Using Static and Transient Tags Vishwa Vinay, Sopan Khosla, Sanket V Mehta, Sahith Thallapally, Gaurav Verma
US Patent No. 10,846,466
| Adobe Inc.
[pdf]
Digital Document Update Vishwa Vinay, Sopan Khosla, Sanket V Mehta, Sahith Thallapally, Gaurav Verma
US Patent No. 10,489,498
| Adobe Inc.
[pdf]