Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Alessandro Oltramari"'
Autor:
Chu-ren Huang, Nicoletta Calzolari, Aldo Gangemi, Alessandro Lenci, Alessandro Oltramari, Laurent Prevot
The relation between ontologies and language is currently at the forefront of natural language processing (NLP). Ontologies, as widely used models in semantic technologies, have much in common with the lexicon. A lexicon organizes words as a conventi
This chapter illustrates how suitable neuro-symbolic models for language understanding can enable domain generalizability and robustness in downstream tasks. Different methods for integrating neural language models and knowledge graphs are discussed.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::39809059ba9ef75c1bd9ac2e62c55bc7
https://doi.org/10.3233/faia210360
https://doi.org/10.3233/faia210360
Autor:
Kaixin Ma, Pedro Szekely, Bin Zhang, Alessandro Oltramari, Deborah L. McGuinness, Filip Ilievski
Commonsense knowledge is essential for many AI applications, including those in natural language processing, visual processing, and planning. Consequently, many sources that include commonsense knowledge have been designed and constructed over the pa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::56a828d0a36ae3fa2151db02f60e309d
http://arxiv.org/abs/2101.04640
http://arxiv.org/abs/2101.04640
Autor:
Faner Lin, Kaixin Ma, Xi Chen, Alessandro Oltramari, Eric Nyberg, Yeju Zhou, Jonathan Francis
Publikováno v:
Proceedings of the 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021).
In this paper, we describe our systems for solving the two Doc2Dial shared task: knowledge identification and response generation. We proposed several pre-processing and post-processing methods, and we experimented with data augmentation by pre-train
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0322c2b282fb96fd4b19493972353cd0
https://doi.org/10.18653/v1/2021.dialdoc-1.14
https://doi.org/10.18653/v1/2021.dialdoc-1.14
Recent developments in pre-trained neural language modeling have led to leaps in accuracy on commonsense question-answering benchmarks. However, there is increasing concern that models overfit to specific tasks, without learning to utilize external k
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2f7501bfb2e03e592e78624119634265
http://arxiv.org/abs/2011.03863
http://arxiv.org/abs/2011.03863
Publikováno v:
Cognitive Systems Research. 48:39-55
In this paper we identify and characterize an analysis of two problematic aspects affecting the representational level of cognitive architectures (CAs), namely: the limited size and the homogeneous typology of the encoded and processed knowledge. We
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::439469471c075a4171c6f90408a87cd2
https://doi.org/10.1016/j.cogsys.2017.05.001
https://doi.org/10.1016/j.cogsys.2017.05.001
Autor:
N. Cameron Russell, Peter Story, Thomas B. Norton, Alessandro Oltramari, Dhivya Piraviperumal, Joel R. Reidenberg, Florian Schaub, Norman Sadeh, Shomir Wilson, Sushain Cherivirala
Publikováno v:
Semantic Web. 9:185-203
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::743487e4e90277bdfc494a026d5fcc49
https://doi.org/10.3233/sw-170283
https://doi.org/10.3233/sw-170283
Publikováno v:
Cognitive Systems Research. 48:1-3
The term "Cognitive Architectures" indicates both abstract models of cognition, in natural and artificial agents, and the software instantiations of such models which are then employed in the field ...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d91e6b2c366bc50babf941a890c77387
https://doi.org/10.1016/j.cogsys.2017.08.003
https://doi.org/10.1016/j.cogsys.2017.08.003
Publikováno v:
IoTDI
Intelligent personalization systems are becoming increasingly reliant on contextually-relevant devices and services, such as those available within modern IoT deployments. An IoT context may emerge---or become pervasive---when the intelligent system
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::02810d6c92e87147fe4747c1de3df349
https://doi.org/10.1145/3054977.3057294
https://doi.org/10.1145/3054977.3057294
Publikováno v:
MILCOM
This paper discusses the use of an ontology to characterize network behavior features. Efficient and timely threat detection requires careful examination of network packets as well as integration of observed packet level behaviors into a coherent vie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b9673a2700ebe7cd6acbf2743903719b
https://doi.org/10.1109/milcom.2016.7795420
https://doi.org/10.1109/milcom.2016.7795420