Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Olga Uryupina"'
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:
Information Processing Management (IPM) journal, 52, 46-60. Elsevier
We designed the first model for effectively carrying out opinion mining on YouTube comments.We propose kernel methods applied to a robust shallow syntactic structure, which improves accuracy for both languages.Our approach greatly outperforms other b
Publikováno v:
EMNLP
Modern automated dialog systems require complex dialog managers able to deal with user intent triggered by high-level semantic questions. In this paper, we propose a model for automatically clustering questions into user intents to help the design ta
Autor:
Heike Zinsmeister, Juntao Yu, Yulia Grishina, Fabian Simonjetz, Nafise Sadat Moosavi, Olga Uryupina, Adam Roussel, Varada Kolhatkar, Alexandra Uma, Massimo Poesio, Ina Roesiger
Publikováno v:
Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference
The ARRAU corpus is an anaphorically annotated corpus of English providing rich linguistic information about anaphora resolution. The most distinctive feature of the corpus is the annotation of a wide range of anaphoric relations, including bridging
Autor:
Olga Uryupina, Alessandro Moschitti
Publikováno v:
CoNLL
Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)
Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)
This paper presents a collaborative partitioning algorithm—a novel ensemble-based approach to coreference resolution. Starting from the all-singleton partition, we search for a solution close to the ensemble’s outputs in terms of a task-specific
Publikováno v:
Soft Computing. 19:2149-2161
In this paper a differential evolution (DE)-based feature selection technique is developed for anaphora resolution in a resource-poor language, namely Bengali. We discuss the issues of adapting a state-of-the-art English anaphora resolution system fo
Autor:
Marius-Iulian Corici, Pedro A. Aranda, Robert Mullins, Angel Martin, Olga Uryupina, Antonio Pastor, Danny Raz, Domenico Gallico, Alberto Mozo, Lei Xu, Bruno Ordozgoiti, Patrick J. O'Sullivan, Imen Grida Ben Yahia, Matteo Biancani, Mikhail Smirnov, Teodora Sandra Buda, Haytham Assem
Publikováno v:
2016 European Conference on Networks and Communications (EuCNC)
EuCNC
EuCNC
It is expected that the fifth generation mobile networks (5G) will support both human-to-human and machine-to-machine communications, connecting up to trillions of devices and reaching formidable levels of complexity and traffic volume. This brings a
Autor:
Olga Uryupina, Roberto Zanoli
Publikováno v:
Anaphora Resolution ISBN: 9783662479087
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aaa04ff0e5836f0f450bb1d3d75377cf
https://doi.org/10.1007/978-3-662-47909-4_7
https://doi.org/10.1007/978-3-662-47909-4_7
Autor:
Angel Martin, Lei Xu, Haytham Assem, Bruno Ordozgoiti, Olga Uryupina, Mikhail Smirnov, Alaa Alloush, Teodora Sandra Buda, Danny Raz, Udi Margolin, Diego R. Lopez, Robert Mullins, Marius-Iulian Corici, Patrick J. O'Sullivan, Alberto Mozo, Imen Grida Ben Yahia, Elisha J. Rosensweig
Publikováno v:
NOMS 2016-2016 IEEE/IFIP Network Operations and Management Symposium
NOMS
NOMS
5G represents the next generation of communication networks and services, and will bring a new set of use cases and scenarios. These in turn will address a new set of challenges from the network and service management perspective, such as network tra
Publikováno v:
Anaphora Resolution ISBN: 9783662479087
Anaphora Resolution-Algorithms, Resources, and Applications
Anaphora Resolution-Algorithms, Resources, and Applications
In this chapter we discuss proposals concerning the detection of non-referentiality and non-anaphoricity, and the integration of such methods in an anaphora resolution system. We first review in brief a number of proposals on the topics, also coverin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c287d649a75fd93e53c7be22fd1e3a56
https://doi.org/10.1007/978-3-662-47909-4_13
https://doi.org/10.1007/978-3-662-47909-4_13