Generating plausible and fluent sentence with desired properties has long been a challenge. Most of the recent works use recurrent neural networks (RNNs) and their variants to predict following words given previous sequence and target label. In this paper, we propose a novel framework to generate constrained sentences via Gibbs Sampling. The candidate sentences are revised and updated iterative...

Aiming at the problem that the identification precision in intonation evaluation and analysis of English sentences is not high, this paper proposes a method of English sentences on the basis of ontology graph clustering evaluation. First, we study the ontology-graph evaluation model of English sentences, conduct objective evaluation to English sentences based on the fundamental framework of KL ...

In this paper, we present an approach to quickly develop supertags for a target language given supertags for another language (reference language), along with a sentence-aligned parallel corpus between reference language and target language pairs. Our method can be interpreted as composing the alignment relation with dependency relation of the reference sentence to obtain the dependency relatio...

In English, high-quality sentence compression models by deleting words have been trained on automatically created large training datasets. We work on Japanese sentence compression by a similar approach. To create a large Japanese training dataset, a method of creating English training dataset is modified based on the characteristics of the Japanese language. The created dataset is used to train...

PURPOSE In this study, the authors investigated sentence comprehension and spatial working memory abilities in a sample of internationally adopted, postinstitutionalized (PI) children. The authors compared the performance of these PI children with that of an age-matched group of children living with their birth families. They hypothesized that PI children would perform below clinical threshold ...

The paper focuses on the annotation of sentence modality in the Prague Dependency Treebank (PDT). Sentence modality (as the contrast between declarative, imperative, interrogative etc. sentences) is expressed by a combination of several means in Czech, from which the category of verbal mood and the final punctuation of the sentence are the most important ones. In PDT 2.0, sentence modality was ...

We developed a new sentence extraction framework, the Sliding Window Framework, by using coherent structure among the sentences. Coherent structure means that the sentences that relate to a certain topic in an article are written in clusters to preserve the logical organization. To use the structure, our method makes blocks that consist of sentences in a window of a certain size, then estimates...