English. In this work, we analyse whether Wikipedia can be used to leverage simplification pairs instead of Simple Wikipedia, which has proved unreliable for assessing automatic simplification systems, and is available only in English. We focus on sentence pairs in which the target sentence is the outcome of a Wikipedia edit marked as ‘simplified’, and manually annotate simplification phenomena...

In this paper, we propose a general formulation of discrete functional regularization on weighted graphs. This framework can be used to on any multi-dimensional data living on graphs of arbitrary topologies. But, in this work, we focus on the microscopic image segmentation and classification with a semi and unsupervised schemes. Moreover, to provide a fast image segmentation we propose a graph ...

Most work on automatic text simplification considers lexical difficulty separate from syntactic simplification. In this study, we use both factors together to predict a variety of sentence changes, including the standard problems of splitting and shortening, as well as expanding to define difficult words that are important to the topic. We leverage a variety of lexical and parse features, as we...

Most recent sentence simplification systems use basic machine translation models to learn lexical and syntactic paraphrases from a manually simplified parallel corpus. These methods are limited by the quality and quantity of manually simplified corpora, which are expensive to build. In this paper, we conduct an indepth adaptation of statistical machine translation to perform text simplification...

The occurrence of syntactic phenomena such as coordination and subordination is characteristic of long, complex sentences. Text simplification systems need to detect and categorise constituents in order to generate simpler sentences. These constituents are typically bounded or linked by signs of syntactic complexity, which include conjunctions, complementisers, whwords, and punctuation marks. T...

Lexical Simplification is the task of modifying the lexical content of complex sentences in order to make them simpler. Due to the lack of reliable resources available for the task, most existing approaches have difficulties producing simplifications which are grammatical and that preserve the meaning of the original text. In order to improve on the state-of-the-art of this task, we propose use...

Sets of attribute implications may have a certain degree of redundancy and the notion of basis appears as a way to characterize the implication set with less redundancy. The most widely accepted is the Duquenne-Guigues basis, strongly based on the notion of pseudo-intents. In this work we propose the minimal generators as an element to remove redundancy in the basis. The main problem is to enum...

In recent years interest in creating statistical automated text simplification systems has increased. Many of these systems have used parallel corpora of articles taken from Wikipedia and Simple Wikipedia or from Simple Wikipedia revision histories and generate Simple Wikipedia articles. In this work we motivate the need to construct a large, accessible corpus of everyday documents along with t...