Martin Szummer's home page
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
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.
- 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
- 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.
- Martin Szummer, Emine Yilmaz
Semi-supervised Learning to Rank with Preference Regularization October 2011.
Conf. Information and Knowledge Management (CIKM) Poster
- Daniel Sheldon, Milad Shokouhi, Martin Szummer, Nick Craswell
Merging the Results of Query Reformulations February 2011.
Web Search and Data Mining (WSDM) Poster
- Martin 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.
- Marc'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
- Lorenzo Torresani, Martin Szummer, Andrew Fitzgibbon. Learning
Query-dependent Prefilters for Scalable Image Retrieval (
supplement ) June 2009. Proc. Comp. Vision Pattern Recogn. (CVPR)
- Nick Craswell, Martin Szummer. Random
Walks on the Click Graph July 2007. SIGIR Conf. Research and
Development in Information Retrieval 239-246
Complete publication list: see short list and
long list (with abstracts).
I have had the privelege to recruit and mentor talented
- Percy Liang, now assistant professor at Stanford
- Yuan Qi, now assistant professor at Purdue
- Balaji Krishnapuram, now senior manager R&D Siemens
- Phil Cowans, now CTO Songkick.com
- Andriy Mnih, now Post-Doc Gatsby unit
- Marc-Aurelio Ranzato, now Researcher, Google X lab
- Roger Grosse, Ph.D. student at MIT
- Volodymyr Mnih, Ph.D student at Univ. of Toronto
- Alex Spengler, Ph.D. student Paris
For personal matters, and for historic interest, you may also refer to
My email address is my last name at media.mit.edu