This paper describes an acceptance test procedure for evaluating a spoken language translation system between Catalan and Spanish. The procedure consists of two independent tests. The first test was an utterance-oriented evaluation for determining how the use of speech benefits communication. This test allowed for comparing relative performance of the different system components, explicitly: so...

Sentences in a well-formed text are connected to each other via various links to form the cohesive structure of the text. Current neural machine translation (NMT) systems translate a text in a conventional sentence-by-sentence fashion, ignoring such cross-sentence links and dependencies. This may lead to generate an incohesive and incoherent target text for a cohesive and coherent source text. ...

BACKGROUND In silico target prediction of compounds plays an important role in drug discovery. The chemical similarity ensemble approach (SEA) is a promising method, which has been successfully applied in many drug-related studies. There are various models available analogous to SEA, because this approach is based on different types of molecular fingerprints. To investigate the influence of tra...

Learning often involves integration of information from multiple texts. The aim of the current study was to determine whether relevant information from previously read texts is spontaneously activated during reading, allowing for integration between texts (experiment 1 and 2), and whether this process is related to the representation of the texts (experiment 2). In both experiments, texts with ...

abstract translation of literary texts, especially poetry, is one of the most difficult tasks; it requires mastery and knowledge of the language system and culture, and lack of this might lead to wrong translation. this study aimed to examine the loss and gain of the sociocultural implicit meanings in the english translations of the mu’allaqat, and assess whether the translators of the mu’allaq...

in this research, different english translations of sa‘di’s bustan were studied. an anecdote was selected randomly with its three english translations to identify whether or not the translators have managed to convey the messages of the original poem. the three selected translations were examined according to two of the criteria that larson (1984) has proposed (accuracy and naturalness) for tes...

The data flow in natural language generation (NLG) starts with a 'world' state, represented by structures of an application program (e.g., an expert system) that has text generation needs and an impetus to produce a natural language text. The output of generation is a natural language text. The generation process involves the tasks of a) delimiting the content of the eventual text, b) plano nin...

The goal of simultaneous speech-to-speech (S2S) translation is to translate source language speech into target language with low latency. While conventional speech-to-speech (S2S) translation systems typically ignore the source language acousticprosodic information such as pausing, exploiting such information for simultaneous S2S translation can potentially aid in the chunking of source text in...

sig Target {} sig Addr extends Target {} abstract sig Name extends Target {} sig Alias, Group extends Name {} sig Book {addr: Name -> Target} Fig. 2.8 shows a model diagram, a graphical representation of the model’s declarations, generated automatically by the analyzer from the text above. Note that the addr field of Book now maps names to targets. A fig. 2.8 Model diagram for hierarchical addr...