CLARIN-EL Web-based Annotation Tool

CLARIN-EL Web-based Annotation Tool Ioannis Manousos Katakis, Georgios Petasis, Vangelis Karkaletsis Institute of Informatics and Telecommunications National Centre for Scientific Research (N.C.S.R.) “Demokritos” GR-153 10, P.O. BOX 60228, Aghia Paraskevi, Athens, Greece {gkatakis, petasis, vangelis}@iit.demokritos.gr Abstract This paper presents a new Web-based annotation tool, the “CLARIN-EL Web-based Annotation Tool”. Based on an existing annotation infrastructure offered by the “Ellogon” language enginneering platform, this new tool transfers a large part of Ellogon’s features and functionalities to a Web environment, by exploiting the capabilities of cloud computing. This new annotation tool is able to support a wide range of annotation tasks, through user provided annotation schemas in XML. The new annotation tool has already been employed in several annotation tasks, including the anotation of arguments, which is presented as a use case. The CLARIN-EL annotation tool is compared to existing solutions along several dimensions and features. Finally, future work includes the improvement of integration with the CLARIN-EL infrastructure, and the inclusion of features not currently supported, such as the annotation of aligned documents. Keywords: Annotation tools, collaborative annotation, adaptable annotation schemas, Web-based annotation tools 1. Introduction The large volumes of data that are being published on the Web every day, create the need for powerful systems able to discover information contained in them. Usually, such kind of systems exploit supervised machine-learning tech- niques, requiring some form of guidance through examples, which are quite often extracted from manually annotated corpora. Although the production of this kind of corpora is a demanding and time-consuming process, it can be signif- icantly facilitated by the use of user-friendly and intuitive annotation tools. In this paper, we present a new Web-based annotation tool which can cover a wide range of annotation tasks, through its support to end-user provided annotation schemas, defin- ing the graphical elements, the tags, and the restrictions that can be used to manually annotate a corpus. The pro- posed annotation solution is based on the relevant desktop, cross-platform annotation tool and the annotation engine provided by the Ellogon language engineering platform1 (Petasis et al., 2002), and attempts to transfer many of its features in a Web environment by exploiting the capabili- ties of cloud computing. Ellogon’s annotation engine is a framework that supports the creation of a wide range of annotation tools, either desk- top applications such as (Fragkou et al., 2008) or collabora- tive tools like (Petasis, 2012a) and (Petasis, 2014) that dis- tribute annotation through a centralised server. The range of annotation tasks that can be implemented include any an- notation task that can be modelled through the selection of multiples text ranges, and group such ranges in annotations, along with user provided information. Under such a model, a wide range of annotation tasks can be accomplished, from morphological annotation (i.e. part-of-speech annotation), to phrase annotation (from syntactic annotation to named entities, sentiment, co-reference, etc.), and up to semantic annotation, where documents can be annotated with a se- mantic model (such as an OWL ontology) (Fragkou et al., 1http://www.ellogon.org 2008). The infrastructure …

Content truncated to 500 words