The role of working class mothers’ talk in explaining their child’s ‘impoverished’ language development and the resulting ‘word gap’ between social classes is hotly debated. Academic research this area spans decades, crosses continents, gathers up a wide range disciplines positions, ranging from seeking to intervene optimise talk, that vigorously criticises any attempt do so. Through an extende...

In this paper, an unsupervised approach for constructing a large-scale Chinese electronic dictionary is surveyed. The main purpose is to enable cheap and quick acquisition of a large-scale dictionary from a large untagged text corpus with the aid of the information in a small tagged seed corpus. The basic model is based on a Viterbi reestimation technique. During the dictionary construction pro...

Definition extraction is the task of automatically identifying definitional sentences within texts. The task has proven useful in many research areas including ontology learning, relation extraction and question answering. However, current approaches – mostly focused on lexicosyntactic patterns – suffer from both low recall and precision, as definitional sentences occur in highly variable synta...

This paper describes three experiments in using frame level observation probabilities as the basis for word confidence annotation in an HMM speech recognition system. One experiment is at the word level, one uses word classes, and the other uses phone classes. In each experiment we categorize hypotheses into correct and incorrect categories by aligning a best recognition hypothesis with the kno...

We describe a novel semi-supervised method called WordCodebook Learning (WCL), and apply it to the task of bionamed entity recognition (bioNER). Typical bioNER systems can be seen as tasks of assigning labels to words in bioliterature text. To improve supervised tagging, WCL learns a class of word-level feature embeddings to capture word semantic meanings or word label patterns from a large unl...

In this work we propose an approach to label probabilistic synchronous context-free grammar (PSCFG) rules using only word tags, generated by either part-of-speech analysis or unsupervised word class induction. Our approach improves translation quality over the single generic label approach of Chiang (2005) on the NIST large resource Chinese-toEnglish translation task. These improvements persist...