Although human-written summaries of documents tend to involve significant edits to the source text, most automated summarizers are extractive and select sentences verbatim. In this work we examine how elementary discourse units (EDUs) from Rhetorical Structure Theory can be used to extend extractive summarizers to produce a wider range of human-like summaries. Our analysis demonstrates that EDU...

Khoy, one of the major cities in the west Azarbaijan province is known for its nature, military, border positions, proximity to the Silk Road, including many different cultures and overall is one of the important settlements in the area. This essay investigates Khoy city’s expansion, from early Islam until late Qajar (Fourth - Fourteenth century) according to historical documents. This article ...

The semantic understanding of domain-specific terminology typical for communities, like a scientific conference, requires both, the analysis of daily spoken and written language in documents. A living taxonomy can help to cluster knowledge and classify questions against it, as well as to build up profiles of expertise. Text analysis modules support the parsing of training materials to extract a...

To enable better representations of biomedical argumentation over collections of research papers, we propose a model and a lightweight ontology to represent interpersonal, discourse-based, data-driven reasoning. This model is applied to a collection of scientific documents, to show how it can be applied in practice. We present three biomedical applications for this work, and suggest connections...

Web Crawlers (also called Web Spiders or Robots), are programs used to download documents from the internet. Simple crawlers can be used by individuals to copy an entire web site to their hard drive for local viewing. For such small-scale tasks, numerous utilities like wget exist. In fact, an entire web crawler can be written in 20 lines of Python code. Indeed, the task is inherently simple: th...

As Chinese text is written without word boundaries, effectively recognizing Chinese words is like recognizing collocations in English, substituting characters for words and words for collocations. However, existing topical models that involve collocations have a common limitation. Instead of directly assigning a topic to a collocation, they take the topic of a word within the collocation as the...

“malakoot” story (literally celestial kingdom), the only novel written by bahram sadeghi, is one of the memorial work that has been witten under the influence of “boof-e-koor” story (literally blind owl) written by sadegh hedayat by a distinctive style and during a specific period of time. aside from unique content of this story, form and structure of this work are also remarkable and marvelous...