In this article we present a novel linguistically driven evaluation method and apply it to the main approaches of Machine Translation (Rule-based, Phrase-based, Neural) to gain insights into their strengths and weaknesses in much more detail than provided by current evaluation schemes. Translating between two languages requires substantial modelling of knowledge about the two languages, about translation, and about the world. Using English-German IT-domain translation as a case-study, we also enhance the Phrase-based system by exploiting parallel treebanks for syntax-aware phrase extraction and by interfacing with Linked Open Data (LOD) for extracting named entity translations in a post decoding framework.
Based on CRFs Approach. – In: Proc. of 2nd International Conference on Recent Trends and Applications in Computer Science and Information Technology, CEUR-WS.org, Vol. 1746 , 2016, pp. 47-52. 4. Rao, D., P. McNamee, M. Dredze. EntityLinking: Finding Extracted Entities in a Knowledge Base. – In: Multi-Source, Multilingual Information Extraction and Summarization, Berlin, Heidelberg, Springer, 2013, pp. 93-115. 5. Arapakis, I., L. A. Leiva, B. B. Cambazoglu. Know Your Onions: Understanding the User Experience with the Knowledge Module in Web Search. – In: Proc. of 24
devise a generic data model to accommodate all our test cases and many more. Our generic data model ( Fig. 1A) has three key components: 1) processual entities, which include things such as collecting specimens, carrying out assays, and analyzing data; 2) material entities such as physical specimens, reagents, and probes; and 3) data entities, including both individual data objects and datasets. We include a project entity as the umbrella under which the other entities are grouped. Processual entitieslink material and data entities in a graph, through input and