We propose a new approach to improving named entity recognition (NER) in broadcast news speech data. The approach proceeds in two key steps: (1) we automatically detect document alignments between highly similar speech documents and corresponding written news stories that are easily obtainable from the Web; (2) we employ term expansion techniques commonly used in information retrieval to recove...

azidahak (zahhak) has always been a strange myth among the other mythological characters in pre-islamic literature. is it possible to figure out a specific historical period for his life? or as avesta's image shows, we should consider him as a semi-human, semi-monster notion with three ugly heads on his shoulder? this article tries to put this figure on the spotlight and illuminate his rea...

Named entity recognition consists of identifying ‘mentions’ — strings in a text that correspond to named entities — and then classifying each such mention as corresponding to a specific type of named entity, with typical categories being Company, Person and Location. The full range of named entity categories to be identified is usually application dependent. Introduced for the first time as a s...

We describe a named-entity tagging system that requires minimal linguistic knowledge and thus may be applied to new target languages without significant adaptation. To maintain a languageneutral posture, the system is linguistically naïve, and in fact, reduces the tagging problem to supervised machine learning. A large number of binary features are extracted from labeled data to train classifie...

emierre’s syndrome consists of a pharyngeal infection assoiated with septicemia and internal jugular thrombosis with eptic emboli. This condition was described in 1936 by ndre Lemierre.1,2 It was initially named as post-anginal epticemia, and then, ‘‘forgotten disease’’, by becoming rare condition after the advent of antibiotics, with fewer han 100 cases reported since 1974.2 Lamierre’s syndrom...