Ontology-Driven Extraction of Research Processes. Pertsas, Vayianos; Constantopoulos, Panos; Androutsopoulos, Ion In: Vrandečić, Denny; Bontcheva, Kalina; Suárez-Figueroa, Mari Carmen; Presutti, Valentina; Celino, Irene; Sabou, Marta; Kaffee, Lucie-Aimée; Simperl, Elena (Ed.): The Semantic Web – ISWC 2018. 17th International Semantic Web Conference, Monterey, CA, USA, October 8–12, 2018, Proceedings, Volume: 11136 of the series Lecture Notes in Computer Science Pages: 162-178, Springer, 2018, ISBN: 978-3-030-00670-9.@inproceedings{Pertsas2018b,
title = {Ontology-Driven Extraction of Research Processes},
author = {Vayianos Pertsas and Panos Constantopoulos and Ion Androutsopoulos},
editor = {Denny Vrandečić and Kalina Bontcheva and Mari Carmen Suárez-Figueroa and Valentina Presutti and Irene Celino and Marta Sabou and Lucie-Aimée Kaffee and Elena Simperl},
doi = {10.1007/978-3-030-00671-6_10},
isbn = {978-3-030-00670-9},
year = {2018},
date = {2018-09-18},
booktitle = {The Semantic Web – ISWC 2018. 17th International Semantic Web Conference, Monterey, CA, USA, October 8–12, 2018, Proceedings},
volume = {11136},
pages = {162-178},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
abstract = {We address the automatic extraction from publications of two key concepts for representing research processes: the concept of research activity and the sequence relation between successive activities. These representations are driven by the Scholarly Ontology, specifically conceived for documenting research processes. Unlike usual named entity recognition and relation extrac- tion tasks, we are facing textual descriptions of activities of widely variable length, while pairs of successive activities often span multiple sentences. We developed and experimented with several sliding window classifiers using Logistic Regression, SVMs, and Random Forests, as well as a two-stage pipeline classifier. Our classifiers employ task-specific features, as well as word, part-of-speech and dependency embeddings, engineered to exploit distinctive traits of research publications written in English. The extracted activities and sequences are associated with other relevant information from publication metadata and stored as RDF triples in a knowledge base. Evaluation on datasets from three disciplines, Digital Humanities, Bioinformatics, and Medicine, shows very promising performance.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We address the automatic extraction from publications of two key concepts for representing research processes: the concept of research activity and the sequence relation between successive activities. These representations are driven by the Scholarly Ontology, specifically conceived for documenting research processes. Unlike usual named entity recognition and relation extrac- tion tasks, we are facing textual descriptions of activities of widely variable length, while pairs of successive activities often span multiple sentences. We developed and experimented with several sliding window classifiers using Logistic Regression, SVMs, and Random Forests, as well as a two-stage pipeline classifier. Our classifiers employ task-specific features, as well as word, part-of-speech and dependency embeddings, engineered to exploit distinctive traits of research publications written in English. The extracted activities and sequences are associated with other relevant information from publication metadata and stored as RDF triples in a knowledge base. Evaluation on datasets from three disciplines, Digital Humanities, Bioinformatics, and Medicine, shows very promising performance.
|
Ontology-Driven Information Extraction from Research Publications. Pertsas, Vayianos; Constantopoulos, Panos In: Méndez, Eva; Crestani, Fabio; Ribeiro, Cristina; David, Gabriel; Lopes, João Correia (Ed.): Digital Libraries for Open Knowledge. TPDL 2018., Volume: 11057 of the series Lecture Notes in Computer Science Pages: 241-253, Springer, 2018, ISBN: 978-3-030-00065-3.@inproceedings{Pertsas2018,
title = {Ontology-Driven Information Extraction from Research Publications},
author = {Vayianos Pertsas and Panos Constantopoulos},
editor = {Eva Méndez and Fabio Crestani and Cristina Ribeiro and Gabriel David and João Correia Lopes},
doi = {10.1007/978-3-030-00066-0_21},
isbn = {978-3-030-00065-3},
year = {2018},
date = {2018-09-05},
booktitle = {Digital Libraries for Open Knowledge. TPDL 2018.},
volume = {11057},
pages = {241-253},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
abstract = {Extraction of information from a research article, association with other sources and inference of new knowledge is a challenging task that has not yet been entirely addressed. We present Research Spotlight, a system that leverages existing information from DBpedia, retrieves articles from repositories, extracts and interrelates various kinds of named and non-named entities by exploiting article metadata, the structure of text as well as syntactic, lexical and semantic constraints, and populates a knowledge base in the form of RDF triples. An ontology designed to represent scholarly practices is driving the whole process. The system is evaluated through two experiments that measure the overall accuracy in terms of token- and entity- based precision, recall and F1 scores, as well as entity boundary detection, with promising results.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Extraction of information from a research article, association with other sources and inference of new knowledge is a challenging task that has not yet been entirely addressed. We present Research Spotlight, a system that leverages existing information from DBpedia, retrieves articles from repositories, extracts and interrelates various kinds of named and non-named entities by exploiting article metadata, the structure of text as well as syntactic, lexical and semantic constraints, and populates a knowledge base in the form of RDF triples. An ontology designed to represent scholarly practices is driving the whole process. The system is evaluated through two experiments that measure the overall accuracy in terms of token- and entity- based precision, recall and F1 scores, as well as entity boundary detection, with promising results.
|
Archaeological Knowledge Production and Global Communities: Boundaries and Structure of the Field. Laužikas, Rimvydas; Dallas, Costis; Thomas, Suzie; Kelpšienė, Ingrida; Huvila, Isto; Luengo, Pedro; Nobre, Helena; Toumpouri, Marina; Vaitkevičius, Vykintas In: Open Archaeology, Volume: 4 (1), Pages: 350–364, 2018, ISSN: 2300-6560.@article{Laužikas2018,
title = {Archaeological Knowledge Production and Global Communities: Boundaries and Structure of the Field},
author = {Rimvydas Laužikas and Costis Dallas and Suzie Thomas and Ingrida Kelpšienė and Isto Huvila and Pedro Luengo and Helena Nobre and Marina Toumpouri and Vykintas Vaitkevičius},
doi = {10.1515/opar-2018-0022},
issn = {2300-6560},
year = {2018},
date = {2018-09-01},
journal = {Open Archaeology},
volume = {4},
number = {1},
pages = {350–364},
abstract = {Archaeology and material cultural heritage enjoys a particular status as a form of heritage that, capturing the public imagination, has become the locus for the expression and negotiation of regional, national, and intra-national cultural identities. One important question is: why and how do contemporary people engage with archaeological heritage objects, artefacts, information or knowledge outside the realm of an professional, academically-based archaeology? This question is investigated here from the perspective of theoretical considerations based on Yuri Lotman’s semiosphere theory, which helps to describe the connections between the centre and peripheries of professional archaeology as sign structures. The centre may be defined according to prevalent scientific paradigms, while periphery in the space of creolisation in which, through interactions with other culturally more distant sign structures, archaeology-related nonprofessional communities emerge. On the basis of these considerations, we use collocation analysis on representative English language corpora to outline the structure of the field of archaeology-related nonprofessional communities, identify salient creolised peripheral spaces and archaeology-related practices, and develop a framework for further investigation of archaeological knowledge production and reuse in the context of global archaeology.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Archaeology and material cultural heritage enjoys a particular status as a form of heritage that, capturing the public imagination, has become the locus for the expression and negotiation of regional, national, and intra-national cultural identities. One important question is: why and how do contemporary people engage with archaeological heritage objects, artefacts, information or knowledge outside the realm of an professional, academically-based archaeology? This question is investigated here from the perspective of theoretical considerations based on Yuri Lotman’s semiosphere theory, which helps to describe the connections between the centre and peripheries of professional archaeology as sign structures. The centre may be defined according to prevalent scientific paradigms, while periphery in the space of creolisation in which, through interactions with other culturally more distant sign structures, archaeology-related nonprofessional communities emerge. On the basis of these considerations, we use collocation analysis on representative English language corpora to outline the structure of the field of archaeology-related nonprofessional communities, identify salient creolised peripheral spaces and archaeology-related practices, and develop a framework for further investigation of archaeological knowledge production and reuse in the context of global archaeology.
|