We present sentence enhancement as a novel technique for text-to-text generation in abstractive summarization. Compared to extraction or previous approaches to sentence fusion, sentence enhancement increases the range of possible summary sentences by allowing the combination of dependency subtrees from any sentence from the source text. Our experiments indicate that our approach yields summary ...

Regulatory text is a complex network of information distinguished by technical language, large volume, and tangled concepts formed by embedded cross-references. Scattering and tangling add to the cognitive pressures on users of regulatory text. Multidimensional Separation of Concerns (MDSOC) is a software engineering method aimed at untangling source code objects that contain cross-cutting, ove...

the present study examines the effect of gender ideology of the translators on two persian translations of emily bronte’s wuthering heights. the findings reveal that although both translations have many similar features in respect to some maxims of translation, in both of them gender ideology of the translator is a key figure in translating the gender related items/parts of the source text, as ...

cognitive science has found out that languages typically make use of conceptual metaphors to concretize abstract meanings. conceptual metaphor explains a target domain which is abstract via a source domain which is concrete. in other words, conceptual metaphor compares an abstract domain with a concrete one and thus makes it understandable for listeners/readers. this article studies the concept...

We are using summarising as a way of studying large-scale discours¢~ structure. Much computationally-orieuted work on disconrse structure ha.s been concerned with dialogue, rather than with 'single-source' text.. Some prop()sals haw. been made for singh~-soul'ce text e.g. l~hetorical Structure Theory (Mann ;rod Tholnpsoll 1987), I)nt al'~' open to criticism (e.g. Moore and I)olla(:k 1.q92); and...

Unlike extractive summarization, abstractive summarization has to fuse different parts of the source text, which inclines to create fake facts. Our preliminary study reveals nearly 30% of the outputs from a state-of-the-art neural summarization system suffer from this problem. While previous abstractive summarization approaches usually focus on the improvement of informativeness, we argue that ...

This paper describes the USAAR-CHRONOS participation in the Diachronic Text Evaluation task of SemEval-2015 to identify the time period of historical text snippets. We adapt a web crawler to retrieve the original source of the text snippets and determine the publication year of the retrieved texts from their URLs. We report a precision score of >90% in identifying the text epoch. Additionally, ...