Avishek Anand

Avishek Anand

Assistant Professor of Information Retrieval

Leibniz Universität Hannover


Avishek Anand is an Assistant Professor in the Leibniz University of Hannover. His research aims to develop intelligent and transparent machine learning approaches to help humans find relevant information. His research broadly falls in the intersection of Machine learning on Web and information retrieval. Specifically, he is interested in scalable and interpretable representation learning methods for text and graphs. He holds a PhD in computer science from the Max Planck Insitute for Informatics, Saarbrücken. His research is supported by Amazon research awards and Schufa Gmbh. He has been a visiting scholar in Amazon Search.


  • Interpretability of learning systems
  • Information Retrieval
  • Representation learning for graphs
  • Scalable representation learning


  • PhD in Information Retrieval, 2013

    Max Planck Insitute for Computer Science, Saarland University

  • MSc in Computer Science, 2009

    Saarland University

  • BTech in Computer Science, 2005

    Indian Institute for Information Technology


Interpretable Machine Learning

Predictive models are all pervasive with usage in search engines, recommender systems, health, legal and financial domains. But for the most part they are used as black boxes which output a prediction, score or rankings without understanding partially or even completely how different features influence the model prediction.

Large Scale Machine Learning

Machine learning models are progressively becoming complex and training datasets are getting larger by the data. Embeddings models are trained over Web scale collections of text and graphs, language models are learnt over millions or billions of sentences.

Information Retrieval

My main focus in information retrieval is currently investigating neural models for ranking models for document retrieval and open-domain question answering. I also work extensively on temporal information retrieval and enrichment of textual knowledge sources like Wikipedia.

Recent & Upcoming Talks

Question Answering over Curated and Open Web Sources

Question Answering over Curated and Open Web Sources

Question Answering over Curated and Open Web Sources

Recent Posts

Recent Publications

A Comparative Study for Unsupervised Network Representation Learning

An In-depth Analysis of Passage-Level Label Transfer for Contextual Document Ranking

BERTnesia: Investigating the capture and forgetting of knowledge in BERT

Explain and Predict, and then Predict Again

Exploiting Sentence-Level Representations for Passage Ranking

Learnt Sparsification for Interpretable Graph Neural Networks

Learnt Sparsity for Effective and Interpretable Document Ranking



Assistant Professor

Leibniz Universität Hannover

Jul 2017 – Present Hannover
Information Retrieval and Machine Learning.

Post-doctoral researcher

L3S Research Center

Feb 2014 – Jul 2017 Hannover

Doctoral researcher

Max Planck Institut für Informatik

Feb 2009 – Jan 2014 Saarbrücken

Software Development Engineer

Microsoft India Research and Development Center

May 2005 – Mar 2007 Hyderabad


  • +49 0511 762 17795
  • Appelstraße 4, Hannover, Niedersachsen 30169
  • Enter Building and take the stairs to Floor 2. My office is the first one on the left.
  • Monday 10:00 to 13:00
    Wednesday 09:00 to 10:00
  • Book an appointment
  • DM Me