While previous studies show that modeling the minimum meaningbearing units (characters or morphemes) benefits learning vector representations of words, they ignore the semantic dependencies across these units when deriving word vectors. In this work, we propose to improve the learning of Chinese word embeddings by exploiting semantic knowledge. The basic idea is to take the semantic knowledge a...

In some contexts, well-formed natural language cannot be expected as input to information or communication systems. In these contexts, the use of grammar-independent input (sequences of uninflected semantic units like e.g. languageindependent icons) can be an answer to the users’ needs. However, this requires that an intelligent system should be able to interpret this input with reasonable accu...

Wikis have been extensively adopted in educational contexts becoming repositories of potentially reusable, self-contained learning units (commonly known as learning objects). Unfortunately, wikis lack of the packaging and metadata facilities that are needed to enable effective reuse of these units. In this article we propose an approach to use semantic wikis as learning object repositories, we ...

Automatic deduction of semantic labels for audiovisual data requires awareness of context, which in turn requires processing sequences of audiovisual scenes or events. The representation of such sequences is important for semantic analysis tasks. Whereas, conventionally, sequences of specific short-duration event labels, often hand-annotated for learning detectors or classifiers, have been used...

We present a transition-based system that jointly predicts the syntactic structure and lexical units of a sentence by building two structures over the input words: a syntactic dependency tree and a forest of lexical units including multiword expressions (MWEs). This combined representation allows us to capture both the syntactic and semantic structure of MWEs, which in turn enables deeper downs...

Estimating similarities at different levels of linguistic units, such as words, sub-phrases and phrases, is helpful for measuring semantic similarity of an entire bilingual phrase. In this paper, we propose a convolution-enhanced bilingual recursive neural network (ConvBRNN), which not only exploits word alignments to guide the generation of phrase structures but also integrates multiple-level ...

The SemEval 2016 DiMSUM Shared Task concerns the detection of minimal semantic units from text and prediction of their coarse lexical categories known as supersenses. Our approach is to define this task as a binary classification problem approachable by straightforward machine learning methods. We start by detecting semantic units by matching text spans against several large dictionaries, inclu...

The article aims to reveal and analyze phraseological paradigm of transformed PUs in the context within two remote cognates. following problems arise: 1) detection analysis semantics semantic structure units; 2) allocation general features using such context; 3) investigation functioning classical works English Russian literature. Semantic, grammatical, componential contextual aspects units are...

• To what extent are semantic tagsets language-specific? • What should be the relationship between lexicai meanings of the language and semantic tags? • Are semantic tags necessarily hierarchically organized? If so, what should tag hierarchies look like? • What are the main methodologies available for the construction of semantic tagsets? • Can semantic tagsets, which are language-specific, be ...

This paper shows how an explicit representation of units and quantities can improve the experience of semantically published documents, and provides a first authoring method in this respect. To exemplify the potential and practical advantages of encoding explicit semantics regarding units w.r.t. user experience, we demonstrate a unit system preference service, which enables the user to choose t...