The domain adaptation capability of information extraction (IE) systems relies on automatic acquisition of domain specific knowledge. The domain specific knowledge contains domain relevant terms, semantic relations for ontology building, or lexicosyntactic patterns for template filling [Riloff & Jones 1999 and Yangarber et al 2000]. Recently, an ever-growing interest in automatic term extractio...

Both formalists and functionalists have proposed that universal phonetic or phonological principles govern early word production, yet the wide range of individual differences in this period continues to resist coherent formulation in such terms, even across children acquiring a single language. This study explores the extent of withinand between-language similarities and differences in phonolog...

Most word embedding models typically represent each word using a single vector, which makes these models indiscriminative for ubiquitous homonymy and polysemy. In order to enhance discriminativeness, we employ latent topic models to assign topics for each word in the text corpus, and learn topical word embeddings (TWE) based on both words and their topics. In this way, contextual word embedding...

multi-word lexical units are a typical feature of specialized dictionaries, in particular monolingual and bilingual maritime dictionaries. the paper studies the concept of the multi-word lexical unit and considers the similarities and differences of their selection and presentation in monolingual and bilingual maritime dictionaries. the work analyses such issues as the classification of multi-w...

Single word recognition experiments have shown that when a word is primed by an orthographic neighbour (e.g. blur primed by blue), reaction times to the target increase (e.g., Davis & Lupker, 2006; De Moor & Brysbaert, 2000; Drews & Zwitserlood, 1995; Nakayama et al., 2008). Models of word recognition like the Interactive Activation (IA) model (McClelland & Rumelhart, 1981) and the SOLAR model ...

First word learning should be difficult because any pairing of a word and scene presents the learner with an infinite number of possible referents. Accordingly, theorists of children's rapid word learning have sought constraints on word-referent mappings. These constraints are thought to work by enabling learners to resolve the ambiguity inherent in any labeled scene to determine the speaker's ...

First word learning should be difficult because any pairing of a word and scene presents the learner with an infinite number of possible referents. Accordingly, theorists of children’s rapid word learning have sought constraints on word-referent mappings. These constraints are thought to work by enabling learners to resolve the ambiguity inherent in any labeled scene to determine the speaker’s ...

Traditional CNN-based text recognition problems have either been single-character classification like MNIST or complex, stateful full-word classifications like the LSTM approach in Graves et al. I explore a stateless approach to word recognition by using Faster R-CNN’s region proposal network in conjunction with a heuristic to produce word labels from region proposals. While the results are pro...

word word P(w) (decision tree) model Although finite-state transducers have been widely used in linguistics, their application to speech recognition has begun only recently [I]. We describe our implementation of French large vocabulary recognition based on transducers, and how we take advantage of this approach to integrate automatic pronunciation rules and cross-word phenomena such as French '...