Photo of Martin Szummer

Martin Szummer

I am a researcher at the University of Cambridge, UK. I am part of the Spoken Dialogue Systems group. Previously, I was a researcher at Microsoft Research in Cambridge, in the machine learning and perception group. I obtained my Ph.D. in machine learning at MIT in 2002, and my M.S. degree at the MIT Media lab.

I develop probabilistic models that describe the structure of data, for example how the pattern of words in a normal email message differs from that of a spam message, or how the pixels in an image are arranged into objects.

Research

Spoken Dialogue Systems
Machines you can talk to.
Methods that control overfitting
I develop Bayesian inference techniques, which do not overfit, because they do not aim to fit - instead they integrate out model parameters. I also work on regularizers that control smoothness by exploiting partially labeled data. Such semi-supervised learning is applicable when large amounts of unlabeled data can be gathered easily, but where we do not have enough human resources to manually label all of the data.
Structured prediction
When making predictions over multiple items, we must model the correlations and interactions between items, in order to make predictions that are consistent across the items. For example, we may need to rank a set of items from best to worst, or classify multiple items (e.g. pixels in an image, a random field).
Flexible models
Data is often complex and our understanding of it is limited. I research deep learning models that can learn complex structure in the data. These include deep belief networks and deep auto-encoders.
Probabilistic programming
We lift the level of abstraction to program in terms of probabilistic models, which allows significantly more complex models to be intuitively expressed and correctly implemented.
Big Data
I work with web-scale datasets, such as records from tens of millions of users, which I process on cloud-based clusters of 10,000 machines, using map-reduce.

Applications

  • Text mining and language understanding. Learning the meaning of phrases from user interactions, data mining of user clicks.
  • Image recognition, image search, handwriting recognition
  • User behavior modeling from clicks, browsing data and computational advertising.

Selected recent publications

Spoken dialog systems

2013M. Gašić, C. Breslin, M. Henderson, D. Kim, M. Szummer, B. Thomson, P. Tsiakoulis, S. Young. POMDP-based dialogue manager adaptation to extended domains. SIGDIAL 2013. Best Paper Award.
2012M. Szummer, M. Henderson, C. Breslin, M. Gašić, D. Kim, B. Thomson, P. Tsiakoulis, S. Young. The BUDS POMDP Dialogue System. Advances in Neural Information Processing Systems (NIPS) Demo 2012.

Information retrieval

2011Martin Szummer, Emine Yilmaz. Semi-supervised Learning to Rank with Preference Regularization. October 2011. Conf. Information and Knowledge Management (CIKM). Poster
2011Daniel Sheldon, Milad Shokouhi, Martin Szummer, Nick Craswell. LambdaMerge: Merging the Results of Query Reformulations. February 2011. Web Search and Data Mining (WSDM). Poster
2009Lorenzo Torresani, Martin Szummer, Andrew Fitzgibbon. Learning Query-dependent Prefilters for Scalable Image Retrieval (supplement). June 2009. Proc. Comp. Vision Pattern Recogn. (CVPR)
2007Nick Craswell, Martin Szummer. Random Walks on the Click Graph. July 2007. SIGIR Conf. Research and Development in Information Retrieval 239-246

Conditional random fields

2010Martin Szummer, Pushmeet Kohli, Derek Hoiem. Learning Random Fields using Graph Cuts. October 2010. Book chapter in book on MRFs, MIT press, edited by Andrew Blake, Carsten Rother, Pushmeet Kohli.

Learning deep networks

2008Marc'Aurelio Ranzato, Martin Szummer. Semi-supervised Learning of Compact Document Representations with Deep Networks. July 2008. Proc. Intl. Conf. on Machine Learning (ICML) 2008 792-799

Complete publication list: without abstracts · with abstracts

Students

I have had the privelege to recruit and mentor talented students, including Percy Liang (now professor at Stanford), Volodymyr Mnih (Google DeepMind), Andriy Mnih (Google DeepMind), Marc-Aurelio Ranzato (Google DeepMind), Roger Grosse (Anthropic and prof. U of Toronto), Yuan Qi (professor at Fudan University), Balaji Krishnapuram (VP at LinkedIn), Phil Cowans (founder & CTO Pi Labs), and Alex Spengler (Microsoft Research).

Personal

For personal matters, and for historic interest, you may also refer to this page.

My email address is my last name at media.mit.edu