Zobrazeno 1 - 10
of 197
pro vyhledávání: '"Alessandro Moschitti"'
Publikováno v:
IJCoL, Vol 3, Iss 2, Pp 51-65 (2017)
In this paper, we developed a deep neural network (DNN) that learns to solve simultaneously the three tasks of the cQA challenge proposed by the SemEval-2016 Task 3, i.e., question-comment similarity, question-question similarity and new question-com
Externí odkaz:
https://doaj.org/article/70270dcef614458ea9deeac0dfdebc17
Publikováno v:
IJCoL, Vol 2, Iss 1, Pp 77-86 (2016)
In this paper, we introduce a Deep Neural Network (DNN) for engineering Named Entity Recognizers (NERs) in Italian. Our network uses a sliding window of word contexts to predict tags. It relies on a simple word-level log-likelihood as a cost function
Externí odkaz:
https://doaj.org/article/4524f7e164484008a35bc7a5fbe1b5b2
Publikováno v:
IEEE Transactions on Knowledge and Data Engineering. 33:3258-3269
In this paper, we present a framework for performing automatic analysis of Land Use Zones based on Location-Based Social Networks (LBSNs). We model city areas using a hierarchical structure of POIs extracted from foursquare. We encode such structures
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::32501c0bfdaf52deb6e9fd439340ed42
https://doi.org/10.1109/tkde.2020.2967381
https://doi.org/10.1109/tkde.2020.2967381
Publikováno v:
Università degli di Trento-IRIS
This paper aims at uncovering the structure of clinical documents, in particular, identifying paragraphs describing “diagnosis” or “procedures”. We present transformer-based architectures for approaching this task in a monolingual setting (En
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b23e693e5c3333ef06f37312442279bb
http://books.openedition.org/aaccademia/10593
http://books.openedition.org/aaccademia/10593
Publikováno v:
Proceedings of the 31st ACM International Conference on Information & Knowledge Management.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::64a16b987c7fc22016bd5bdb62a368d1
https://doi.org/10.1145/3511808.3557678
https://doi.org/10.1145/3511808.3557678
Publikováno v:
AAAI
We propose TANDA, an effective technique for fine-tuning pre-trained Transformer models for natural language tasks. Specifically, we first transfer a pre-trained model into a model for a general task by fine-tuning it with a large and high-quality da
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9939be026e936a13ff0594e93d42ae3
https://doi.org/10.1609/aaai.v34i05.6282
https://doi.org/10.1609/aaai.v34i05.6282
Publikováno v:
ACL/IJCNLP (Findings)
Recent advancements in transformer-based models have greatly improved the ability of Question Answering (QA) systems to provide correct answers; in particular, answer sentence selection (AS2) models, core components of retrieval-based systems, have a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1a11e685f6396c89690259d8a46a37f6
http://arxiv.org/abs/2106.00955
http://arxiv.org/abs/2106.00955
Publikováno v:
AAAI
Kernel methods are popular and effective techniques for learning on structured data, such as trees and graphs. One of their major drawbacks is the computational cost related to making a prediction on an example, which manifests in the classification
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f7e293640b46ed1852a32becbb9924f1
https://doi.org/10.1609/aaai.v33i01.33013421
https://doi.org/10.1609/aaai.v33i01.33013421
Autor:
Alessandro Moschitti, Lingzhen Chen
Publikováno v:
AAAI
In this paper, we propose an approach for transferring the knowledge of a neural model for sequence labeling, learned from the source domain, to a new model trained on a target domain, where new label categories appear. Our transfer learning (TL) tec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ceb54bcab2f67901164a3171a34926a0
https://doi.org/10.1609/aaai.v33i01.33016260
https://doi.org/10.1609/aaai.v33i01.33016260
Autor:
Hamdy Mubarak, Giovanni Da San Martino, Mohamed Eldesouki, James Glass, Alberto Barrón-Cedeño, Alessandro Moschitti, Yonatan Belinkov, Salvatore Romeo, Kareem Darwish
Publikováno v:
Information Processing & Management. 56:274-290
In this paper we focus on the problem of question ranking in community question answering (cQA) forums in Arabic. We address the task with machine learning algorithms using advanced Arabic text representations. The latter are obtained by applying tre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::722b2daaf82008ab6a40dcb331d530c1
https://doi.org/10.1016/j.ipm.2017.07.003
https://doi.org/10.1016/j.ipm.2017.07.003