Andrea Galassi Home Page

Andrea Galassi Home Page a.galassi@unibo.it Wed, 07/03/2018 - 15:19

 

Andrea Galassi

2nd year PhD student

DISI, Università di Bologna
Viale del Risorgimento 2, 40136 - Bologna (IT)

email: a<dot>galassi<at>unibo<dot>it

Profiles:

 

I am a second year PhD student at the Computer Science and Engineer department (DISI) of the University of Bologna. My supervisor is Professor Paolo Torroni.

My PhD is focused on the application of Artificial Intelligence and Machine Learning techniques to Argumentation Mining and similar Natural Language Processing tasks.

My research interests involve also the investigation of what Deep Networks can achieve by themselves and possible ways to combine symbolic and sub-symbolic techniques. So far, we have conducted our investigation on board games and Constraint Satisfaction Problems.

I've been teaching assistant ("Tutor Didattico") of professors Paola Mello, Federico Chesani, and Paolo Torroni. I am one of the responsible of the Board Game Students Challenge. I am also co-supervisor in some bachelor thesis, masters thesis, and course projects, most of them regarding machine learning application.

I have visited Stanford University during summer 2018, working under the supervision of Margaret Hagan in the context of the MIREL project.

 

Recent works and news:

 

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 and Research Material

Publications and Research Material a.galassi@unibo.it Wed, 13/02/2019 - 16:35

NLP

Pre-print

Attention, please! A Critical Review of Neural Attention Models in Natural Language Processing

Presentation

Attention - a useful tool to improve and understand neural networks

Conference Paper

Argumentative Link Prediction using Residual Networks and Multi-Objective Learning

Cite as:

Andrea Galassi, Marco Lippi, and Paolo Torroni. 2018. Argumentative link prediction using residual networks and multi-objective learning. In Proceedings of the 5th Workshop on Argument Mining, pages 1–10. Association for Computational Linguistics. URL: http://aclweb.org/anthology/W18-5201

Presentation

Argumentative Link Prediction Using Residual Networks and Multi-Objective Learning

 

Deep Networks and CSPs

Conference Paper

Model agnostic solution of CSPs via Deep Learning: a preliminary study

Cite as:

Galassi A., Lombardi M., Mello P., Milano M. (2018) Model Agnostic Solution of CSPs via Deep Learning: A Preliminary Study. In: van Hoeve WJ. (eds) Integration of Constraint Programming, Artificial Intelligence, and Operations Research. CPAIOR 2018. Lecture Notes in Computer Science, vol 10848. Springer, Cham. DOI: 10.1007/978-3-319-93031-2_18

Presentation:

Deep Neural Networks for CSP, an initial investigation

 

Games

Journal Paper

Can Deep Networks Learn to Play by the Rules? A Case Study on Nine Men’s Morris

Cite as:

F. Chesani, A. Galassi, M. Lippi and P. Mello, "Can Deep Networks Learn to Play by the Rules? A Case Study on Nine Men's Morris," in IEEE Transactions on Games, vol. 10, no. 4, pp. 344-353, Dec. 2018. DOI: 10.1109/TG.2018.2804039
 

Code

 

Project Page

 

Education

Conference Paper

A Game-Based Competition as Instrument for Teaching Artificial Intelligence

Cite as:

Chesani F., Galassi A., Mello P., Trisolini G. (2017) A Game-Based Competition as Instrument for Teaching Artificial Intelligence. In: Esposito F., Basili R., Ferilli S., Lisi F. (eds) AI*IA 2017 Advances in Artificial Intelligence. AI*IA 2017. Lecture Notes in Computer Science, vol 10640. Springer, Cham. DOI: 10.1007/978-3-319-70169-1_6

Poster

 

 

Attention, please! A Critical Review of Neural Attention Models in Natural Language Processing

Attention, please! A Critical Review of Neural Attention Models in Natural Language Processing a.galassi@unibo.it Mon, 29/04/2019 - 16:57

Publicly Accessible Resources