Prefer reading text instead?


Nandan Thakur

NLP Researcher @ UKP Lab, TU Darmstadt
Pronouns: (he/him)
[Email] [LinkedIn] [GitHub] [Twitter] [Google Scholar] [ORCID]

Recent News

  • (06/2021): Will be attending NAACL 2021, Come and Say Hi.
  • (05/2021): An active collaboration with Pyserini (UWaterloo)
    on improving existing IR benchmarks. [code]
  • (05/2021): BEIR was one of the few preprint papers to feature
    in Stanford CS224u course on NLU+IR. [slides]
  • (05/2021): BEIR Public Leaderboard is now online. [link]
  • (04/2021): BEIR preprint is now available on Arxiv. [link]
  • (03/2021): Augmented SBERT got accepted in NAACL 2021!!
  • (02/2021): Designed and Attended The First ELLIS NLP 2021
    Workshop Website. [link]
  • (01/2021): Designed SustaiNLP 2021 Website. [link]
  • (11/2020): [Cancelled (COVID-19)] Selected to speak at PyCon
    Italia 2020: "Extract or Replace Keywords in sentences 28x
    times faster than Regex - FlashText". [Abstract] [YouTube] [Github]
  • (7/2020): ArgumenText won 4th place amongst 3000+ startups
    in Nordbayerischen Businessplan. [link]
  • (7/2020): I attended the Association for Computational
    Linguistics (ACL) 2020 virtual conference.

  • Publications

  • BEIR: A Heterogenous Benchmark for Zero-Shot Evaluation
    of Information Retrieval (IR) Models.

    Nandan Thakur, Nils Reimers, Andreas Rücklé, Abhishek Srivastava,
    Iryna Gurevych. in ArXiv (2021). [PDF] [Code] [Leaderboard]
  • Augmented SBERT: Data Augmentation Method for Improving
    Bi-Encoders for Pairwise Sentence Scoring Tasks.

    Nandan Thakur, Nils Reimers, Johannes Daxenberger, Iryna Gurevych.
    NAACL 2021. [PDF] [Code] [Blog] [bib]

  • About Me

    Hello! I am a full-time research assistant at the Ubiquitous Knowledge Processing (UKP) Lab at the Technical University of Darmstadt. I have been fortunate to be supervised by Prof. Dr. Iryna Gurevych and mentored by Dr. Nils Reimers. My primary research interests lie in the area of Natural Language Processing and Information Retrieval. My long-term research ambition lies in improving low-resource and data-scarce NLP, a practical setting useful for both research and industry.

    Prior to UKP, I worked as a Data Scientist in the Industry for a year. I graduated with B.E. (Hons.) in Electronics and Instrumentation from Birla Institute of Technology and Science (BITS) Pilani, India. Personally, I love football and I'm a passionate Chelsea FC supporter. I love to cook and travel unknown beauties. I am impulsive and I like impromptu hikes, bike trips, or treks in nature.

    I am currently exploring Research Oppertunities (PhD) in Natural Language Processing (NLP) around USA, UK or Europe. If you find my profile relevant, feel free to contact me on any of my social handles mentioned below or leave me a message here. I speak English, Hindi and Bengali fluently. I am learning German (A2).

    Efficient & Low-Resource NLP

    Sentence Embeddings, Transformer Architectures, Information Retrieval

    Deep Learning & Machine Learning

    HuggingFace, PyTorch/

    BERT, T5, GPT-3

    Backend and Frontend Development

    Flask, Python, Docker,

    VueJS, CSS, HTML

    Data Science and Analytics

    Numpy, Pandas, Scikit-Learn,

    NLTK, SpaCy, Gensim

    My Blogs