| A83-1013 | as a formal query . However cur | extractor | , unlike the equivalent processors |
| A00-1041 | capitalization in titles and headings . The | extractor | uses various heuristics , including |
| C00-1012 | such extracts vary ; so do human | extractors | . Sentence extraction systems |
| A92-1043 | a chart parser and a headnoun | extractor | . The symbolic chart parser built |
| A97-1052 | , Classifier and Evaluator The | extractor | takes as input the ranked analyses |
| A97-1052 | 15 % of patterns found by the | extractor | when run on all the patternsets |
| A97-1052 | parsed automatically , and the | extractor | , classifier and evaluator were |
| A94-1043 | sentence ana - lyzer , an information | extractor | and a rewriting candidate generator |
| A92-1043 | syntactic lexicon . Then the headnoun | extractor | retrieved the sequence of headnouns |
| A00-1041 | proper names . The proper-name | extractor | essentially classifies capitalized |
| A97-1046 | section , the CLARIT noun phrase | extractor | is used to extract all the noun |
| A83-1013 | the paper , to save space . The | extractor | is geared to seek , in the analyser |
| A97-1052 | comprehensive subcategorization class | extractor | is able both to assign classes |
| A97-1052 | the system that are new : the | extractor | , classifier and evaluator . |
| A94-1043 | trees provided by the information | extractor | . 4 . Experiment and Evaluation |
| A92-1043 | microcomputer software " . This headnoun | extractor | was motivated by the close relationship |
| A94-1043 | accumulated as rules for the information | extractor | , which is actually a general-purpose |
| A83-1013 | is also an attractive one . The | extractor | thus emphasises the fact that |
| A94-1028 | of nominal compounds . The pair | extractor | looks at the distribution statistics |
| A97-1052 | basis of the behaviour of the | extractor | . We estimate this probability |
