Andrea Galassi Home Page
|
Andrea Galassi Post Doc Research Fellow DISI, Università di Bologna email: a<dot>galassi<at>unibo<dot>it |
Profiles: |
Research fellow and Ajdunct Professor at the Computer Science and Engineering Department (DISI) of the University of Bologna.
I've recently defended my PhD thesis, which is focused on the use of Machine Learning and Artificial Intelligence techniques, especially neural-symbolic techniques, on the topic of Argumentation Mining. Neural-symbolic techniques mix traditional symbolic approaches with neural ones with the purpose to obtain models that are performative but are also reliable and explainable.
Argumentation Mining is a branch of Natural Language Processing that concerns the automatic extraction of arguments from unstructured texts.
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 have covered the role of adjunct professor and teaching assistant in several university courses, for a total amount of more than 200 hours. My experience ranges from introductory courses of the bachelor degree, such as Foundations of Computer Science, to advanced courses of the master degree, such as Natural Language Processing.
Recent works and news:
- Aug 2021: Our paper "An Argumentative Dialogue System for COVID-19 Vaccine Information" has been accepted for CLAR 2021. The pre-print is available here.
- Jun 2021: Our paper "SubjectivITA: An Italian Corpus for Subjectivity Detection in Newspapers" has been accepted for CLEF 2021.
- May 2021: I have defended my PhD thesis "Deep Networks and Knowledge: from Rule Learning to Neural-Symbolic Argument Mining".
- May 2021: We have been invited to NLLP talks to give a talk about our work "Cross-lingual Annotation Projection in Legal Texts". The recording of the talk is available here.
- Feb 2021: Our preprint "Multi-Task Attentive Residual Networks for Argument Mining" is under peer review.
- Dec 2020: Our paper "Cross-lingual Annotation Projection in Legal Texts" has been presented at COLING 2020. Our poster can be found here.
- Sep 2020: Our paper "Neural-Symbolic Argumentation Mining: an Argument in Favor of Deep Learning and Reasoning" will be presented in the Sister and Journal Track of the ICLP2020 conference.
- Aug 2020: Our paper "Attention in Natural Language Processing" has been accepted for publication in IEEE Transactions on Neural Networks and Learning Systems. A presentation on the topic is available here.
- Jan 2020: Our paper "Neural-Symbolic Argumentation Mining: an Argument in Favor of Deep Learning and Reasoning" has been published on "Frontiers in Big Data". It is available for free on the website of the journal.
- Jun 2019: Our abstract "Imitation or Understanding? Deep Learning to the Test on Constraint Satisfaction Problems" has been presented at EURO19.
- Mar 2019: Our paper "HABITAT: An IoT Solution for Independent Elderly" has been published on "Sensors". It is freely available on the website of the journal.
- Feb 2019: Our paper "Attention, please! A Critical Review of Neural Attention Models in Natural Language Processing" is under peer review. A preliminary version is available on arXiv. A presentation on the topic 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. A presentation on the topic can be found here.
- Feb 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 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 can be found here.
Projects in which I am or I've been involved:
- Humane AI: European Network of Human-Centered Artificial Intelligence
- Claudette: Machine Learning Powered Analysis of Consumer Contracts and Privacy Policies
- 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