| other,1-3-H94-1034,ak | </term> or as fluent speech . Other <term> | contextual clues | </term> , such as <term> editing terms </term> | #27222 Othercontextual clues, such as editing terms, word fragments, and word matchings, are also factored in by modifying the transition probabilities. | |
| tech,12-1-H94-1034,ak | <term> speech repairs </term> that uses a <term> | part-of-speech tagger | </term> . The <term> tagger </term> is given | #27188 This paper describes a method of detecting speech repairs that uses apart-of-speech tagger. | |
| other,19-2-H94-1034,ak | repairs </term> , and so is able to mark a <term> | transition | </term> either as a likely <term> repair </term> | #27210 The tagger is given knowledge about category transitions for speech repairs, and so is able to mark atransition either as a likely repair or as fluent speech. | |
| tech,1-2-H94-1034,ak | <term> part-of-speech tagger </term> . The <term> | tagger | </term> is given knowledge about <term> category | #27192 Thetagger is given knowledge about category transitions for speech repairs, and so is able to mark a transition either as a likely repair or as fluent speech. | |
| other,24-2-H94-1034,ak | transition </term> either as a likely <term> | repair | </term> or as fluent speech . Other <term> | #27215 The tagger is given knowledge about category transitions for speech repairs, and so is able to mark a transition either as a likelyrepair or as fluent speech. |
