In this paper, we explore a novel framework to generate a well-known text cloud visualization with the conceptual sense. The traditional text cloud is usually generated according to the word occurrence, possibly including the idf-based concept for word weight. The solution is applicable for the long articles. However, for a set of short sentences such as daily news titles, we cannot easily unde...

In this paper, we develop an RST-style textlevel discourse parser, based on the HILDA discourse parser (Hernault et al., 2010b). We significantly improve its tree-building step by incorporating our own rich linguistic features. We also analyze the difficulty of extending traditional sentence-level discourse parsing to text-level parsing by comparing discourseparsing performance under different ...

A system is described that uses a mixed-level representation of (part of) the meaning of natural language documents (based on standard Horn Clause Logic) and a variable-depth search strategy that distinguishes between the different levels of abstraction in the knowledge representation to locate specific passages in the documents. Mixed-level representations as well as variabledepth search strat...

Motivation: The amount of information widely available in electronic form is growing at an enormous rate. It is generally accepted that this holds great promise for applications as diverse as basic research, news, entertainment, and on-line social communities. Generally useful techniques for sifting through this mostly unstructured stuff are in great demand, as can be seen by the proliferation ...

This paper reports on approaches for automatically predicting a learner’s language proficiency in Estonian according to the European CEFR scale. We used the morphological and POS tag information extracted from the texts written by learners. We compared classification and regression modeling for this task. Our models achieve a classification accuracy of 79% and a correlation of 0.85 when modeled...

Various memory o rgan iza t ion schemes have been proposed in the l as t f i v e years . Lots of i n t e l l i g e n t computer systems have been experimenting w i t h memory schemes l i k e s c r i p t s , p lans , goa l s , 14] and MOPs [5 ] in the domain of t ex t understanding [3 ] [1 ] and in fo rmat ion r e t r i e v a l [ 2 ] . In t h i s paper, the focus is on the problem of t r a n s l...

This paper presents the results of classifying Serbian text documents using the byte-level n-gram based frequency statistics technique, employing four different dissimilarity measures. Results show that the byte-level n-grams text categorization, although very simple and language independent, achieves very good accuracy.

This paper introduces a method for the automatic discrimination of digital images based on their semantic content. The proposed system allows to detect if a digital image contains or not a text document. This is realized by a multi-steps procedure based on low-level feature’s set properly derived. Our experiments show that the proposed algorithm is competitive in efficiency with classical techn...

We present a new model for text regression that seamlessly combine engineered features and character-level information through deep parallel convolution stacks, multi-layer perceptrons and multitask learning. We use these models to create the SHEF/CNN systems for the sentence-level Quality Estimation task of WMT 2017 and Emotion Intensity Analysis task of WASSA 2017. Our experiments reveal that...