About me

My name is Michele (yes, Michele with just one "L") and I am a PhD student at CDT in the School of Computer Science (The University of Manchester). I am member of the gnTEAM and MLO research groups. My PhD research is funded by the EPSRC.

I am obsessed by the following question: Can computers understand time?

My research attempts to positively answer that question by designing a software that exhibits such peculiar human mind's characteristic. I am interested in measuring, in an objective way, what is the performance difference between such software and a person. Finally, I sometimes challenge myself in figuring out some interesting new applications of such technology.

Now, suppose we've got the following document:

The director of Google's self-drive car project has revealed his motivation for ensuring that the technology is standard on roads within five years. Chris Urmson told delegates at the TED conference that his eldest son was 11-years-old and due to take his driving test in "four and a half years". "My team are committed to making sure that doesn't happen," he said. "Some 1.2 million people are killed on the roads around the world each year. That number is equivalent to a jet falling out of the sky every day." The incremental changes some car-makers are introducing are not enough, he said. "That is not to say that driver-assistance cars won't be useful but if we are really going to make changes to our cities, get rid of parking lots, we need self-drive cars," he said.

Understanding the general orientation of this article is very easy for a person (if she can read English). The article mainly talks about events that will happen in the future: more precisely in 5 years (by the date of its publication). At that point Chris' eldest son will be about 16-year-old and, according to the data provided, 6 million people will have died on the roads by car accidents.

Well, how can we make a computer infer all this temporal facts by reading the text? That's my research!

Click to see where I am.

Projects

Temporal query intent classification at Temporalia challenge (NTCIR-11)

New! Temporal query intent prediction!

Temporal footprints demo online: predict temporal boundaries of Wikipedia pages

Demo! Temporal footprint discovery

ManTIME demo online: Temporal information extraction

Demo! ManTIME: Temporal information extraction

TMStats: NLP challenge simulator

Extra! TMStats: how reliable an NLP challenge rank can be?

Google Web 1T with Raspberry Pi

Extra Web interface for Google Web 1T corpus using just a Raspberry Pi!

Poster: Extracting and interpreting temporal information from text, 2013

poster Extracting and interpreting temporal information from text, 2013

Poster: Temporal information extraction in the clinical domain, 2012

poster Temporal information extraction in the clinical domain, 2012

Raspberry Pi LEGO case, 2013

Extra Raspberry Pi LEGO case, 2013

Similarity Algorithm based on WikipediA

Master SAWA: Similarity Algorithm based on WikipediA

Research

Publications

Using machine learning to predict temporal orientation of search engines' queries in the Temporalia challenge
M. Filannino, G. Nenadic
Proceedings of the Sixth International Workshop on Evaluating Information Access (EVIA 2014) a Satellite Workshop of the NTCIR-11 Conference

paper, poster, slides, review, demo, project page, source code.

Mining temporal footprints from Wikipedia
M. Filannino, G. Nenadic
Proceedings of the 1st AHA! Workshop on Information Discovery in Text (COLING 2014)

paper, poster, reviews, bibtex, project page, source code.

Combining rules and machine learning for extraction of temporal expressions and events from clinical narratives
A. Kovačević , A. Dehghan , M. Filannino , J. A. Keane , G. Nenadic
Journal of the American Medical Informatics Association (JAMIA)

paper, poster, bibtex, software.

ManTIME: Temporal expression identification and normalization in TempEval-3 challenge
M. Filannino, G. Brown, G. Nenadic
Proceedings of the 7th International Workshop on Semantic Evaluation (SemEval 2013)

paper, poster, reviews, bibtex, demo, project page, source code.

Temporal expression normalisation in natural language texts
M. Filannino
CoRR, abs/1206.2010, 2012

DBWorld e-mail classification using a very small corpus
M. Filannino
Unpublished (Machine Learning course project)

paper, data set, raw data.

More on Google Scholar

Presentations

11th December 2014
Using machine learning to predict temporal orientation of search engines’ queries in the Temporalia challenge, The 11th NTCIR Conference, NTCIR-11, Tokyo, Japan
23rd August 2014
Mining temporal footprints from Wikipedia, 1st AHA! Workshop on Information Discovery in Text, COLING 2014, Dublin, Ireland
29th October 2013
Extracting and interpreting temporal information from text (awarded with Honourable Mention from IBM), School Research Symposium, Manchester, UK
1st May 2013
Can computers understand time?, Languages @ Leeds PGR Seminars, University of Leeds, Leeds, UK
2nd November 2012
Extraction of temporal expressions, events and relations from clinical narratives using rules and machine-learning, 6th i2b2 Workshop on Challenges in NLP for Clinical Data, Chicago, USA
30th October 2012
Temporal information extraction in the clinical domain, School Research Symposium, Manchester, UK
5th March 2012
Detecting novel associations in large data sets, GN-TEAM Internal presentation, Manchester, UK
29th February 2012
Temporal expressions identification in biomedical texts, Scientific Methods II, Manchester, UK
15th February 2012
My research taster project: temporal expression extraction, GN-TEAM Internal presentation, Manchester, UK
2011
Nonlinear component analysis as a kernel eigenvalue problem, Modelling and visualization of high-dimensional data, Manchester, UK

Other downloads

Side projects

Raspberry Pi LEGO case

Matt Shardlow and I are trying to build a web server for Google Web 1T 5-gram corpus out of a Raspberry Pi. First step: a cool LEGO case!

Here you can download the LEGO model file with the colours of the University of Manchester. :P

Contacts

Office

Room IT301, IT Building
School of Computer Science
The University of Manchester
Manchester, M13 9PL
United Kingdom
Map

I support

World Wildlife Fund For Nature
RainForest Foundation
Ganda Foundation Ltd - Empowered and Sustainable Communities in Uganda