Research
Publications
My research focuses on enhancing the reliability and interpretability of language understanding systems and improving the efficiency of deep learning models. I am particularly interested in the evaluation of sentence acceptability and how language models can be guided by structured representations and human judgments. I also focus on unsupervised methods for information extraction and summarization in real-world applications like e-commerce. Another key area of interest is the integration of external signals, such as weather data, to improve predictive modeling. Overall, my work aims to bridge linguistic insights with practical, scalable machine learning solutions.
Papers
- Vijay Daultani, Hector Javier Vazquez Martinez, Naoaki Okazaki, Acceptability Evaluation of Naturally Written Sentences, IPSJ Transactions on Databases (IPSJ TOD), 2024.
[DOI] - Vijay Daultani, Naoaki Okazaki, Improving Automatic Evaluation of Acceptability Based on Language Models with a Coarse Sentence Representation, Pacific Asia Conference on Language, Information and Computation (PACLIC), 2022.
[URL] - Jeremiah Anderson, Vijay Daultani, Tariq Muman, Mohamed Batran, The Importance of Weather to E-Commerce Orders Forecasting, IEEE International Conference on E-Business Engineering (EBEE), 2019.
[DOI] - Vijay Daultani, Lasguido Nio, Young-Joo Chung, Unsupervised Extractive Summarization for Product Description using Coverage Maximization with Attribute Concept, IEEE International Conference on Semantic Computing (ICSC), 2019.
[DOI] - Vijay Daultani, Ohno Yoshiyuki, Ishizaka Kazuhisa, Sparse Direct Convolutional Neural Network, International Symposium on Neural Networks (ISNN), 2017.
[DOI] [URL] - Vijay Daultani, Subhajit Chaudhury, Ishizaka Kazuhisa, Convolutional Neural Network Layer Reordering for Acceleration, Synthesis And System Integration of Mixed Information Technologies (SASIMI), 2016.
[URL]
Patents
Four inventions granted as six patents in the United States and Japan. My patents have been cited as prior art in later filings by Samsung, Microsoft, Google, Intel, Sony, Canon, JPMorgan Chase, Walmart and others.
Granted
- Information Processing System, Information Processing Method, and Program: Robin Swezey, Jing Mi, Vijay Daultani. Assignee: Rakuten Group.
Granted: US 11,487,835 B2 (Nov. 2022), JP 6655223 B1 (Feb. 2020)
Cited by later patents from Canon, Naver, Xiaomi and NTT Communications.
[US Patent] [JP Patent] - Summary Generating Device, Summary Generating Method, and Information Storage Medium: Vijay Daultani, Lasguido Nio, Youngjoo Chung. Assignee: Rakuten Group.
Granted: US 11,061,950 B2 (Jul. 2021)
Cited in 9 later patent families, including filings by JPMorgan Chase, Walmart, Yahoo and Fujifilm.
[US Patent] - Instruction Selection for a Compiler (Information Processing Apparatus, Information Processing Method and Storage Medium Storing Program): Vijay Daultani. Assignee: NEC.
Granted: US 10,922,061 B2 (Feb. 2021), JP 6642738 B2 (Feb. 2020)
Cited by a later Microsoft compiler optimization patent.
[US Patent] [JP Patent] - Search System, Search Method, and Program: Vijay Daultani. Assignee: Rakuten Group.
Granted: JP 6560843 B1 (Aug. 2019)
Cited in 5 later patent families, including filings by Fujitsu, Kawasaki Heavy Industries and Capital One.
[JP Patent]
Other Filings
- Improved Sparse Convolutional Neural Network: Vijay Daultani. Assignee: NEC. PCT application PCT/JP2016/081973, filed Oct. 2016 (lapsed).
Cited as prior art in 31 later patent families, including filings by Samsung, Microsoft, Google, Intel and Alibaba.
[Link] - Information Processing Method and Device for Neural Network: Vijay Daultani. Assignee: NEC. PCT application PCT/JP2016/068741, filed Jun. 2016 (lapsed).
Cited by later patents from Sony and Samsung.
[Link]
Presentations
- Bringing India to the Forefront of AI Research
Venue: IEEE World Conference on Cutting Edge Science & Technology
Date: Sep. 25 2025
[Presentation] [Website] - From Engineering Students to AI Research Leaders: India’s Path Forward
Venue: Sage University
Date: Aug. 20 2025
[Presentation] - Bringing India at the Forefront of AI Research
Venue: Sage University
Date: Apr. 16 2025
[Presentation] - Imminent AI: Generative Adversarial Networks
Venue: Rakuten Technology Conference
Date: Nov. 9 2019
[Video] - Recurrent Neural Networks
Venue: Rakuten Technology Conference
Date: Oct. 28 2017
[Presentation] [Video] - Association Rules
Venue: Internal Presentation at Rakuten
Date: March 2017
[Presentation]
White Papers
- Bringing India at the Forefront of AI Research
[Link]