A character-level recurrent neural network (RNN) is a statistical language model capable of producing text that superficially resembles a training corpus. The efficacy of these networks in mimicking Shakespeare, Linux source code, and other forms of text have already been demonstrated. In this paper, we show that character-level RNNs are capable of very believably mimicking the language of Pres...

Determining the language proficiency level required to understand a given text is a key requirement in vetting documents for use in second language learning. In this work, we describe our approach for developing an automatic text analytic to estimate the text difficulty level using the Interagency Language Roundtable (ILR) proficiency scale. The approach we take is to use machine translation to...

Scientific articles exhibit a fairly conventionalized structure in terms of topic types such as background, researchTopic, method and their ordering and rhetorical interrelations. This paper describes an effort to make such structures explicit by providing a corpus of German linguistic articles with XML markup according to a text type schema defining 21 topic type categories. The corpus is furt...

Text interpretation can be considered as the process of extracting deep-level semantics from unstructured text documents. Deeplevel semantics represent abstract index structures that enhance the precision and recall of information retrieval tasks. In this work we discuss the use of ontologies as valuable assets to support the extraction of deep-level semantics in the context of a generic archit...

Word representation models have achieved great success in natural language processing tasks, such as relation classification. However, it does not always work on informal text, and the morphemes of some misspelling words may carry important shortdistance semantic information. We propose a hybrid model, combining the merits of word-level and character-level representations to learn better repres...

This paper reports the performances of shallow word-level convolutional neural networks (CNN), our earlier work (2015) [3, 4], on the eight datasets with relatively large training data that were used for testing the very deep characterlevel CNN in Conneau et al. (2016) [1]. Our findings are as follows. The shallow word-level CNNs achieve better error rates than the error rates reported in [1] t...

Social media texts are often written in a non-standard style and include many lexical variants such as insertions, phonetic substitutions, abbreviations that mimic spoken language. The normalization of such a variety of non-standard tokens is one promising solution for handling noisy text. A normalization task is very difficult to conduct in Japanese morphological analysis because there are no ...