In conventional speech translation systems, Automatic Speech Recognition (ASR) produces a single hypothesis which is then translated by the SMT system. The translation results of SMT system are impaired by the word errors of the first best hypothesis in this approach more or less. To improve speech translation, we use a new word lattice translation approach which integrates multiple information...

In this paper we present first experiments towards a tighter coupling between Automatic Speech Recognition (ASR) and Statistical Machine Translation (SMT) to improve the overall performance of our speech translation system. In coventional speech translation systems, the recognizer outputs a single hypothesis which is then translated by the SMT system. This approach has the limitation of being l...

This study examined whether amnesic patients and normal subjects can acquire novel associations implicitly and whether such learning can occur rapidly in a single trial. In two experiments, subjects studied novel word pairs either once or multiple times and were then asked to read old, new, and recombined word pairs as quickly as possible. In this paradigm, the learning of novel associations wo...

Automatically extracting topics from large amounts of text is one the main uses natural language processing (NLP). The latent Dirichlet allocation (LDA) technique frequently used to extract pre-processed materials based on word frequency. One problems LDA that extracted are poor quality if document does not coherently belong a single topic. However, Gibbs sampling operates word-by-word basis, w...

Abstract Children learn words in ambiguous situations, where multiple objects can potentially be referents for a new word. Yet, researchers debate whether children maintain single word-object hypothesis – and revise it if falsified by later information or establish network of associations whose relative strengths are modulated with experience. To address this issue, we presented 4- to 12-year-o...

It is a common assumption that prosodic restrictions on the shape of children’s early productions refer to the prosodic word (cf. [1]). However, empirical research on word structure has focused almost exclusively on simplex words where the morphosyntactic and prosodic word boundaries coincide ([2], [3], [4], [5]). In this paper, we provide new evidence from the acquisition of German complex wor...

Distributed word representations are widely used for modeling words in NLP tasks. Most of the existing models generate one representation per word and do not consider different meanings of a word. We present two approaches to learn multiple topic-sensitive representations per word by using Hierarchical Dirichlet Process. We observe that by modeling topics and integrating topic distributions for...