Neuroimaging studies have shown that speech comprehension involves a number of widely distributed regions within the frontal and temporal lobes. We aimed to examine the differential contributions of white matter connectivity to auditory word and sentence comprehension in chronic post-stroke aphasia. Structural and diffusion MRI data were acquired on 40 patients with chronic post-stroke aphasia....

Text classification in general is a well studied area. However, classifying short and noisy text remains challenging. Feature sparsity is a major issue. The quality of document representation here has a great impact on the classification accuracy. Existing methods represent text using bag-of-word model, with TFIDF or other weighting schemes. Recently word embedding and even document embedding a...

Spoken monologues feature greater sentence length and structural complexity than do spoken dialogues. To achieve high parsing performance for spoken monologues, it could prove effective to simplify the structure by dividing a sentence into suitable language units. This paper proposes a method for dependency parsing of Japanese monologues based on sentence segmentation. In this method, the depen...

This paper deals with sentence-level sentiment classification. Though a variety of neural network models have been proposed recently, however, previous models either depend on expensive phrase-level annotation, most of which has remarkably degraded performance when trained with only sentence-level annotation; or do not fully employ linguistic resources (e.g., sentiment lexicons, negation words,...

A patient (M.L.) with selective disruption of sentence production is described. M.L.'s sentence production performance is characterized by the omission (and occasional substitution) of free-standing and bound grammatical morphemes. In contrast to her impaired sentence production performance, M.L. has no difficulties in sentence comprehension or production of single words including functors. Her...

Let a sentence be second-level indeterminate just in case it has different truth-values under different acceptable assignments of semantic values, and let a sentence be first-level indeterminate just in case there are acceptable assignments under which the sentence lacks a classical, determinate truth-value. Many theorists of vagueness take for granted that the indeterminacy with which vaguenes...

In this paper we combine our previous research in the field of Semantic web, especially ontology learning and population with Sentence retrieval. To do this we developed a new approach to sentence retrieval modifying our previous TF-ISF method which uses local context information to take into account only document level information. This is quite a new approach to sentence retrieval, presented ...

We derive two variants of a semi-supervised model for fine-grained sentiment analysis. Both models leverage abundant natural supervision in the form of review ratings, as well as a small amount of manually crafted sentence labels, to learn sentence-level sentiment classifiers. The proposed model is a fusion of a fully supervised structured conditional model and its partially supervised counterp...

Multi-document summarization is a process of automatic generation of a compressed version of the given collection of documents. Recently, the graph-based models and ranking algorithms have been actively investigated by the extractive document summarization community. While most work to date focuses on homogeneous connecteness of sentences and heterogeneous connecteness of documents and sentence...

Sentence-level sentiment analysis, as a research direction in natural language processing, has been widely used various fields. In order to address the problem that syntactic features were neglected previous studies on sentence-level multiscale graph attention network (MSGAT) analysis model based dependent syntax is proposed. The adopts RoBERTa_WWM text encoding layer, generates graphs basis of...