Andrea Galassi Home Page
|
Andrea Galassi 1st year PhD student DISI, Università di Bologna email: a<dot>galassi<at>unibo<dot>it |
Profiles: |
I am a first year PhD student at the DISI department of the University of Bologna, working on Machine Learning techniques applied to Argumentation Mining, but also to Games and Constraint Satisfaction Problems. My supervisor is Professor Paolo Torroni.
For my Master Thesis, I've applied Deep Neural Networks to a board game, Nine Men's Morris, generating a dataset useful for future Machine Learning work and investigating the ability of the DNNs to learn the rules of a game from scratch. More information about this study are available here.
We have expanded it to the subject of Constraint Satisfaction Problems, to understand whether DNNs can solve problems just by watching some solutions.
For my PhD, I'm studying Argumentation Mining and related topics, working on how to merge symbolic and subsymbolic techniques.
I've been teaching assistant ("Tutor Didattico") of professors Paola Mello, Federico Chesani, and Paolo Torroni. I am also co-supervisor in some bachelor thesis, maters thesis, and course projects, most of them regarding machine learning application.
I have visited the Stanford University during the summer 2018, working under the supervision of Margaret Hagan in the contex of the MIREL project.
Recent works and news:
- Dec 2018: Our paper "Can Deep Networks Learn to Play by the Rules? A Case Study on Nine Men's Morris" has been published on "IEEE Transaction on Games". The accepted version can be found here.
- Nov 2018: Our paper "Argumentative Link Prediction using Residual Networks and Multi-Objective Learning" has been presented at ArgMining2018, a workshop collocated with EMNLP2018. The presentation is available here.
- Jun 2018: Our short paper "Model agnostic solution of CSPs via Deep Learning: a preliminary study" has been presented at CPAIOR 2018. The free pre-publish version can be found here.
- Feb 2018: Our extended abstract "Deep Neural Networks for Constraint Satisfaction Problems: an Initial Investigation for the N-Queens" has been presented at OLA18.
- Nov 2017: Our paper "A Game-Based Competition as Instrument for Teaching Artificial Intelligence" has been presented at AI*IA 2017. The free pre-publish version and the poster can be found here.
Projects in which I am or I've been involved:
- Argumentation Mining: extraction of arguments from unstructured textual documents
- Games and AI: application of Artificial Intelligence techniques in the context of games
- Habitat: Home Assistance Based on the Internet of Things for the AuTonomy
- DeepOpt
Publications
] 