Vipul Raheja
email:  [first].[last]@grammarly[dot]com

Bio | Google Scholar
Semantic Scholar
Linkedin | Github | Twitter

I am an Applied Research Scientist at Grammarly. I work on developing robust and scalable approaches centered around improving the quality of written communication, leveraging Natural Language Processing and Machine Learning. My research interests lie at the intersection of large language models and controllable text generation for text revision. I also co-organize the Workshop on Intelligent and Interactive Writing Assistants (In2Writing).

I frequently collaborate with Dongyeop Kang and his amazing group at Minnesota NLP. Previously, I worked at x.ai on end-to-end Natural Language Understanding (NLU) for conversational AI scheduling assistance. I received my Masters from Columbia University advised by Prof. Luis Gravano and Prof. Tony Jebara. I got a dual-degree in Computer Science (Bachelors and Masters by Research) from IIIT Hyderabad advised by Prof. K. S. Rajan, where I worked on modeling spatio-temporally evolving phenomena, such as foodborne illnesses.


  News
[2024]

2 papers (mEdIT & ContraDoc) accepted to NAACL 2024!

[2024]

2 papers (CoBBLER & Threads of Subtlety) accepted to ACL 2024!

[2024]

Paper accepted at the PERSONALIZE Workshop at EACL 2024.

[2023]

2 papers (CoEdIT & SpeakerlyTM) accepted to EMNLP 2023 (Findings and Industry Track)!

[2023]

Upcoming Invited Talks at QCon SF, Data Science Salon SF, and NLP Summit 2023.

[2023]

Talk at ConvAI Workshop at ACL 2023.

[2023]

Paper accepted at the TrustNLP Workshop @ ACL 2023.

[2023]

Co-organizing the In2Writing Workshop at CHI 2023.

[2023]

Invited Talk at Bugout.dev meetup.

[2023]

Talk and Panel Discussion at RE-WORK Summit, 2023.

[2022]

Paper accepted at EMNLP 2022.

[2022]

Invited Talk at Swiggy Bytes.

[2022]

Best paper award at the In2Writing Workshop at ACL 2022.

[2022]

Co-organizing the In2Writing Workshop at ACL 2022.

[2022]

Paper accepted at ACL 2022.

[2021]

Paper accepted at EACL 2021.

[2020]

Paper accepted at EMNLP 2020.


  Collaborators and Interns
Rickard Stureborg
(Duke University)

Writing with Large Language Models.
Research Intern at Grammarly. Hosted with Vivek Kulkarni.

James Mooney
(University of Minnesota)

Efficient LLM Inference.
Research Intern at Grammarly.

Ryan Koo
(University of Minnesota)

LLMs for Intelligent Writing Assistance.

Risako Owan
(University of Minnesota)

Human Preference Learning.

Bashar Alhafni
(New York University)

Personalized Text Generation.
Research Intern at Grammarly.

Jierui Li
(UT Austin)

Document-level reasoning with LLMs.
Research Intern at Grammarly. Hosted with Dhruv Kumar.

Zae Myung Kim
(University of Minnesota)

Human-in-the-loop Iterative Text Revision.
Research Intern at Grammarly.

Olexandr Yermilov
(Ukrainian Catholic University)

Privacy- and Utility-preserving NLP.
Research Intern at Grammarly. Hosted with Artem Chernodub.

Wanyu Du
(University of Virginia)

Iterative Text Revision.
Research Intern at Grammarly.


  Publications

   Please refer to Google Scholar or Semantic Scholar for the most up-to-date list.

 2022

sym

Improving Iterative Text Revision by Learning Where to Edit from Other Revision Tasks
Zae Myung Kim, Wanyu Du, Vipul Raheja, Dhruv Kumar, Dongyeop Kang
Empirical Methods in Natural Language Processing (EMNLP 2022)

pdf | abstract | bibtex | blog

@inproceedings{kim-etal-2022-improving,
    title = "Improving Iterative Text 
    Revision by Learning Where to 
    Edit from Other Revision Tasks",
    author = "Kim, Zae Myung  and
      Du, Wanyu  and
      Raheja, Vipul  and
      Kumar, Dhruv  and
      Kang, Dongyeop",
    booktitle = "Proceedings of the 2022 
    Conference on Empirical Methods in 
    Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, 
    United Arab Emirates",
    publisher = "Association for 
    Computational Linguistics",
    url = "https://aclanthology.org/
    2022.emnlp-main.678",
    pages = "9986--9999",
}
sym

Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision
Wanyu Du, Zae Myung Kim, Vipul Raheja, Dhruv Kumar, Dongyeop Kang
In2Writing @ Association for Computational Linguistics (ACL 2022)
🏆 Best Paper Award

pdf | abstract | bibtex | video | code

@inproceedings{du-etal-2022-read,
    title = "Read, Revise, Repeat: A 
    System Demonstration for 
    Human-in-the-loop Iterative 
    Text Revision",
    author = "Du, Wanyu  and
      Kim, Zae Myung  and
      Raheja, Vipul  and
      Kumar, Dhruv  and
      Kang, Dongyeop",
    booktitle = "Proceedings of the 
    First Workshop on Intelligent 
    and Interactive Writing 
    Assistants 
    (In2Writing 2022)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for 
    Computational Linguistics",
    url = "https://aclanthology.org/
    2022.in2writing-1.14",
    doi = "10.18653/v1/2022.in2writing-1.14",
    pages = "96--108",
}
sym

Understanding Iterative Revision from Human-Written Text
Wanyu Du, Vipul Raheja, Dhruv Kumar, Zae Kim, Melissa Lopez, Dongyeop Kang
Association for Computational Linguistics (ACL 2022)

pdf | abstract | bibtex | code | blog

@inproceedings{du-etal-2022-
understanding-iterative,
    title = "Understanding Iterative 
    Revision from Human-Written Text",
    author = "Du, Wanyu  and
      Raheja, Vipul  and
      Kumar, Dhruv  and
      Kim, Zae Myung  and
      Lopez, Melissa  and
      Kang, Dongyeop",
    booktitle = "Proceedings of the 
    60th Annual Meeting of the Association
     for Computational Linguistics 
     (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for 
    Computational Linguistics",
    url = "https://aclanthology.org/
    2022.acl-long.250",
    doi = "10.18653/v1/2022.acl-long.250",
    pages = "3573--3590",
}

 2021

sym

Text Simplification by Tagging
Kostiantyn Omelianchuk, Vipul Raheja, Oleksandr Skurzhanskyi
BEA @ European Chapter of the Association of Computational Linguistics (EACL 2021)

pdf | abstract | bibtex | code | blog

@inproceedings{omelianchuk-etal-2021-text,
    title = "{T}ext {S}implification by {T}agging",
    author = "Omelianchuk, Kostiantyn  and
      Raheja, Vipul  and
      Skurzhanskyi, Oleksandr",
    booktitle = "Proceedings of the 16th Workshop 
    on Innovative Use of NLP for Building 
    Educational Applications",
    month = apr,
    year = "2021",
    address = "Online",
    publisher = "Association for 
    Computational Linguistics",
    url = "https://aclanthology.org/2021.bea-1.2",
    pages = "11--25",
}

 2020

sym

Adversarial Grammatical Error Correction
Vipul Raheja, Dimitris Alikaniotis
Empirical Methods in Natural Language Processing (EMNLP 2020)

pdf | abstract | bibtex | blog

@inproceedings{raheja-alikaniotis
-2020-adversarial,
    title = "{A}dversarial {G}rammatical 
    {E}rror {C}orrection",
    author = "Raheja, Vipul  and
      Alikaniotis, Dimitris",
    booktitle = "Findings of the 
    Association for Computational 
    Linguistics: EMNLP 2020",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for 
    Computational Linguistics",
    url = "https://aclanthology.org/2020
    .findings-emnlp.275",
    doi = "10.18653/v1/2020.findings-
    emnlp.275",
    pages = "3075--3087",
}

 2019

sym

The Unreasonable Effectiveness of Transformer Language Models in Grammatical Error Correction
Dimitris Alikaniotis, Vipul Raheja
BEA @ Association of Computational Linguistics (ACL 2019)

pdf | abstract | bibtex | blog

@inproceedings{alikaniotis-raheja-2019-unreasonable,
    title = "The Unreasonable Effectiveness of 
    Transformer Language Models in 
    Grammatical Error Correction",
    author = "Alikaniotis, Dimitris  and
      Raheja, Vipul",
    booktitle = "Proceedings of the Fourteenth 
    Workshop on Innovative Use of NLP 
    for Building Educational Applications",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for 
    Computational Linguistics",
    url = "https://aclanthology.org/W19-4412",
    doi = "10.18653/v1/W19-4412",
    pages = "127--133",
}
sym

Dialogue Act Classification with Context-Aware Self-Attention
Vipul Raheja, Joel Tetreault
North American Chapter of the Association for Computational Linguistics (NAACL 2019)
🏆 State of the art

pdf | abstract | bibtex | blog

@inproceedings{raheja-tetreault-2019-dialogue,
    title = "{D}ialogue {A}ct {C}lassification 
    with {C}ontext-{A}ware {S}elf-{A}ttention",
    author = "Raheja, Vipul  and
      Tetreault, Joel",
    book title = "Proceedings of the 2019 
    Conference of the North {A}merican Chapter 
    of the Association for Computational 
    Linguistics: Human Language Technologies, 
    Volume 1 (Long and Short Papers)",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational 
    Linguistics",
    url = "https://aclanthology.org/N19-1373",
    doi = "10.18653/v1/N19-1373",
    pages = "3727--3733",
}

  Invited Talks & Panels

  Blog Posts

  Past Publications (Data Mining)


Modified version of template from here