We propose new automatic evaluation metric to evaluate machine translation. Different from most similar metrics, our proposed metric does not depend heavily on sentence length. In most metrics based on f-measure comparisons of reference and candidate translations, the relative weight of each mismatched word in short sentences is larger than it in long sentences. Therefore, the evaluation score ...

Why are young children's utterances short? This elicited imitation study used a new task--double imitation--to investigate the factors that contribute to children's failure to lexicalize sentence subjects. Two-year-olds heard a triad of sentences singly and attempted to imitate each; they then again heard the same triad singly and again attempted to imitate each. Comparisons between the two att...

We investigated the potential influence of implicit learning mechanisms on L2 morphosyntactic attainment by examining relationship between age onset (AoO), two cognitive abilities hypothesized to underlie (phonological short-term memory and statistical learning), performance an auditory grammaticality judgment test (GJT). Participants were 71 Polish-English long-term bilinguals with a wide rang...

Event-related potentials were used to investigate whether semantic integration in discourse is influenced by the number of intervening sentences between the endpoints of integration. Readers read discourses in which the last sentence contained a critical word that was either congruent or incongruent with the information introduced in the first sentence. Furthermore, for the short discourses, th...