In this article, we propose a Category Theory approach to (syntactic) interoperability between linguistic tools. The resulting category consists of textual documents, including any linguistic annotations, NLP tools that analyze texts and add additional linguistic information, and format converters. Format converters are necessary to make the tools both able to read and to produce different output formats, which is the key to interoperability. The idea behind this document is the parallelism between the concepts of composition and associativity in Category Theory with the NLP pipelines. We show how pipelines of linguistic tools can be modeled into the conceptual framework of Category Theory and we successfully apply this method to two real-life examples. Paper submitted to Applied Category Theory 2020 and accepted for Virtual Poster Session
Miriam Baglioni; Alessia Bardi; Argiro Kokogiannaki; Paolo Manghi; Katerina Iatropoulou; Pedro Príncipe; André Vieira; Lars Holm Nielsen; Harry Dimitropoulos; Ioannis Foufoulas; +7 more
Miriam Baglioni; Alessia Bardi; Argiro Kokogiannaki; Paolo Manghi; Katerina Iatropoulou; Pedro Príncipe; André Vieira; Lars Holm Nielsen; Harry Dimitropoulos; Ioannis Foufoulas; Natalia Manola; Claudio Atzori; Sandro La Bruzzo; Emma Lazzeri; Michele Artini; Michele De Bonis; Andrea Dell’Amico;
Despite the hype, the effective implementation of Open Science is hindered by several cultural and technical barriers. Researchers embraced digital science, use “digital laboratories” (e.g. research infrastructures, thematic services) to conduct their research and publish research data, but practices and tools are still far from achieving the expectations of transparency and reproducibility of Open Science. The places where science is performed and the places where science is published are still regarded as different realms. Publishing is still a post-experimental, tedious, manual process, too often limited to articles, in some contexts semantically linked to datasets, rarely to software, generally disregarding digital representations of experiments. In this work we present the OpenAIRE Research Community Dashboard (RCD), designed to overcome some of these barriers for a given research community, minimizing the technical efforts and without renouncing any of the community services or practices. The RCD flanks digital laboratories of research communities with scholarly communication tools for discovering and publishing interlinked scientific products such as literature, datasets, and software. The benefits of the RCD are show-cased by means of two real-case scenarios: the European Marine Science community and the European Plate Observing System (EPOS) research infrastructure. This work is partly funded by the OpenAIRE-Advance H2020 project (grant number: 777541; call: H2020-EINFRA-2017) and the OpenAIREConnect H2020 project (grant number: 731011; call: H2020-EINFRA-2016-1). Moreover, we would like to thank our colleagues Michele Manunta, Francesco Casu, and Claudio De Luca (Institute for the Electromagnetic Sensing of the Environment, CNR, Italy) for their work on the EPOS infrastructure RCD; and Stephane Pesant (University of Bremen, Germany) his work on the European Marine Science RCD. First Online 30 August 2019
We propose a morphologically informed model for named entity recognition, which is based on LSTM-CRF architecture and combines word embeddings, Bi-LSTM character embeddings, part-of-speech (POS) tags, and morphological information. While previous work has focused on learning from raw word input, using word and character embeddings only, we show that for morphologically rich languages, such as Bulgarian, access to POS information contributes more to the performance gains than the detailed morphological information. Thus, we show that named entity recognition needs only coarse-grained POS tags, but at the same time it can benefit from simultaneously using some POS information of different granularity. Our evaluation results over a standard dataset show sizable improvements over the state-of-the-art for Bulgarian NER. named entity recognition; Bulgarian NER; morphology; morpho-syntax
We investigated the evolution and transformation of scientific knowledge in the early modern period, analyzing more than 350 different editions of textbooks used for teaching astronomy in European universities from the late fifteenth century to mid-seventeenth century. These historical sources constitute the Sphaera Corpus. By examining different semantic relations among individual parts of each edition on record, we built a multiplex network consisting of six layers, as well as the aggregated network built from the superposition of all the layers. The network analysis reveals the emergence of five different communities. The contribution of each layer in shaping the communities and the properties of each community are studied. The most influential books in the corpus are found by calculating the average age of all the out-going and in-coming links for each book. A small group of editions is identified as a transmitter of knowledge as they bridge past knowledge to the future through a long temporal interval. Our analysis, moreover, identifies the most disruptive books. These books introduce new knowledge that is then adopted by almost all the books published afterwards until the end of the whole period of study. The historical research on the content of the identified books, as an empirical test, finally corroborates the results of all our analyses. 19 pages, 9 figures
Multilingualism is a cultural cornerstone of Europe and firmly anchored in the European treaties including full language equality. However, language barriers impacting business, cross-lingual and cross-cultural communication are still omnipresent. Language Technologies (LTs) are a powerful means to break down these barriers. While the last decade has seen various initiatives that created a multitude of approaches and technologies tailored to Europe's specific needs, there is still an immense level of fragmentation. At the same time, AI has become an increasingly important concept in the European Information and Communication Technology area. For a few years now, AI, including many opportunities, synergies but also misconceptions, has been overshadowing every other topic. We present an overview of the European LT landscape, describing funding programmes, activities, actions and challenges in the different countries with regard to LT, including the current state of play in industry and the LT market. We present a brief overview of the main LT-related activities on the EU level in the last ten years and develop strategic guidance with regard to four key dimensions. Proceedings of the 12th Language Resources and Evaluation Conference (LREC 2020). To appear
Lexical Markup Framework (LMF) or ISO 24613  is a de jure standard that provides a framework for modelling and encoding lexical information in retrodigitised print dictionaries and NLP lexical databases. An in-depth review is currently underway within the standardisation subcommittee , ISO-TC37/SC4/WG4, to find a more modular, flexible and durable follow up to the original LMF standard published in 2008. In this paper we will present some of the major improvements which have so far been implemented in the new version of LMF. Comment: AsiaLex 2019: Past, Present and Future, Jun 2019, Istanbul, Turkey
Publisher: Multidisciplinary Digital Publishing Institute
The historic view of metadata as “data about data” is expanding to include data about other items that must be created, used, and understood throughout the data and project life cycles. In this context, metadata might better be defined as the structured and standard part of documentation, and the metadata life cycle can be described as the metadata content that is required for documentation in each phase of the project and data life cycles. This incremental approach to metadata creation is similar to the spiral model used in software development. Each phase also has distinct users and specific questions to which they need answers. In many cases, the metadata life cycle involves hierarchies where latter phases have increased numbers of items. The relationships between metadata in different phases can be captured through structure in the metadata standard, or through conventions for identifiers. Metadata creation and management can be streamlined and simplified by re-using metadata across many records. Many of these ideas have been developed to various degrees in several Geoscience disciplines and are being used in metadata for documenting the integrated life cycle of environmental research in the Arctic, including projects, collection sites, and datasets.
This paper describes a corpus of about 3000 English literary texts with about 250 million words extracted from the Gutenberg project that span a range of genres from both fiction and non-fiction written by more than 130 authors (e.g., Darwin, Dickens, Shakespeare). Quantitative Narrative Analysis (QNA) is used to explore a cleaned subcorpus, the Gutenberg English Poetry Corpus (GEPC) which comprises over 100 poetic texts with around 2 million words from about 50 authors (e.g., Keats, Joyce, Wordsworth). Some exemplary QNA studies show author similarities based on latent semantic analysis, significant topics for each author or various text-analytic metrics for George Eliot's poem 'How Lisa Loved the King' and James Joyce's 'Chamber Music', concerning e.g. lexical diversity or sentiment analysis. The GEPC is particularly suited for research in Digital Humanities, Natural Language Processing or Neurocognitive Poetics, e.g. as training and test corpus, or for stimulus development and control. 27 pages, 4 figures
International audience; The CENDARI infrastructure is a research-supporting platform designed to provide tools for transnational historical research, focusing on two topics: medieval culture and World War I. It exposes to the end users modern Web-based tools relying on a sophisticated infrastructure to collect, enrich, annotate, and search through large document corpora. Supporting researchers in their daily work is a novel concern for infrastructures. We describe how we gathered requirements through multiple methods to understand historians' needs and derive an abstract workflow to support them. We then outline the tools that we have built, tying their technical descriptions to the user requirements. The main tools are the note-taking environment and its faceted search capabilities; the data integration platform including the Data API, supporting semantic enrichment through entity recognition; and the environment supporting the software development processes throughout the project to keep both technical partners and researchers in the loop. The outcomes are technical together with new resources developed and gathered, and the research workflow that has been described and documented.
This paper addresses the integration of a Named Entity Recognition and Disambiguation (NERD) service within a group of open access (OA) publishing digital platforms and considers its potential impact on both research and scholarly publishing. The software powering this service, called entity-fishing, was initially developed by Inria in the context of the EU FP7 project CENDARI and provides automatic entity recognition and disambiguation using the Wikipedia and Wikidata data sets. The application is distributed with an open-source licence, and it has been deployed as a web service in DARIAH's infrastructure hosted by the French HumaNum. In the paper, we focus on the specific issues related to its integration on five OA platforms specialized in the publication of scholarly monographs in the social sciences and humanities (SSH), as part of the work carried out within the EU H2020 project HIRMEOS (High Integration of Research Monographs in the European Open Science infrastructure). In the first section, we give a brief overview of the current status and evolution of OA publications, considering specifically the challenges that OA monographs are encountering. In the second part, we show how the HIRMEOS project aims to face these challenges by optimizing five OA digital platforms for the publication of monographs from the SSH and ensuring their interoperability. In sections three and four we give a comprehensive description of the entity-fishing service, focusing on its concrete applications in real use cases together with some further possible ideas on how to exploit the annotations generated. We show that entity-fishing annotations can improve both research and publishing process. In the last chapter, we briefly present further possible application scenarios that could be made available through infrastructural projects.