Despite the existence of effective methods that solve named entity recognition tasks for such widely used languages as English, there is no clear answer which methods are the most suitable for languages that are substantially different. In this paper we attempt to solve a named entity recognition task for Lithuanian, using a supervised machine learning approach and exploring different sets of f...

The following work describes a method to automatically classify the sense selection of the complex type Location/Organization –which depends on regular polysemy– using shallow features, as well as a way to increase the volume of sense-selection gold standards by using monosemous data as filler. The classifier results show that grammatical features are the most relevant cues for the identificati...

This paper describes a hybrid proposal to combine n-grams and Stochastic Context-Free Grammars (SCFGs) for language modeling. A classical n-gram model is used to capture the local relations between words, while a stochastic grammatical model is considered to represent the long-term relations between syntactical structures. In order to de ne this grammatical model, which will be used on large-vo...

The purpose of this study was to investigate the effect of textual enhancement types on English as Foreign Language ( EFL ) learn er s ’ grammatical awareness of simple and complex structures. A nu m- ber of 104 learners from Ayandegan Institute, in Tehran, participated in this study. To homogenize the samples, the researchers administered a placement Michigan Test of English language to the p...

Usually writing teachers feel commitment to provide their learners with corrective feedback (CF) to their linguistic errors. The study investigated whether two types of written corrective feedback, indirect focused corrective feedback and indirect unfocused corrective feedback, produced differential effects on the accurate use of grammatical forms by high intermediate EFL learners. In this stud...

We improve automatic correction of grammatical, orthographic, and collocation errors in text using a multilayer convolutional encoder-decoder neural network. The network is initialized with embeddings that make use of character Ngram information to better suit this task. When evaluated on common benchmark test data sets (CoNLL-2014 and JFLEG), our model substantially outperforms all prior neura...