Avishek Anand

Avishek Anand

Associate Professor

Delft University of Technology

Biography

Avishek Anand is an Associate Professor in the Web Information Systems (WIS) at the Software Technology department at Delft University of Technology (TU Delft). His research aims to develop intelligent and transparent machine learning approaches to help humans find relevant information. Specifically, he is interested in Explainable Information Retrieval. He holds a PhD in computer science from the Max Planck Insitute for Informatics, Saarbr├╝cken. Previously, he was an Assistant professor in Information Retrieval in Lebniz University Hannover. His research is supported by Amazon research awards, Schufa Gmbh, BMBF, and EU Horizon 2020. He is also a member of the L3S Research Center and a visiting scholar in Amazon Search.

Interests

  • Interpretability of learning systems
  • Deep learning for search

Education

  • PhD in Information Retrieval, 2013

    MPI Informatik & Saarland University

  • MSc in Computer Science, 2009

    Saarland University

  • BTech in Computer Science, 2005

    Indian Institute for Information Technology

Research

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.

Meet the Team

Researchers

Avatar

Abhijit Anand

PhD Student

Deep learning for search

Avatar

Florian Knauf

PhD Student

Deep learning for search

Avatar

Jonas Wallat

PhD Student

Probing deep learning models, Interpretability for search and news recommendation, AI for precision medicine

Avatar

Jurek Leonhardt

PhD Student

Deep learning for search

Avatar

Lijun Lyu

PhD Student

Utility-driven Interpretability

Avatar

Mandeep Rathee

PhD Student

Interpretability of Graph neural networks

Avatar

Maximillian Idahl

PhD Student

Utility-driven Interpretability

Avatar

Yumeng Wang

PhD Student

Adversarial and Counterfactual attacks on Ranking Models

Avatar

Zijian Zhang

PhD Student

Utility-driven Interpretability

News

BOOK: Question Answering for the Curated Web

We have a new book on Question Answering techniques on knowledge graphs and textual sources. We cover the principles and state-of-the-art QA systems. This book provides a unified view on QA for aspiring graduate students and researchers.
BOOK: Question Answering for the Curated Web

Tutorial: Question Answering over Curated and Open Web Sources

Question Answering over Curated and Open Web Sources
Tutorial: Question Answering over Curated and Open Web Sources

Recent Posts

Recent Publications

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