| other,42-6-A92-1027,bq | only <term> edges </term> with a valid <term> | semantic | </term> interpretation are ever introduced | #17745 A further reduction in the search space is achieved by using semantic rather than syntactic categories on the terminal and non-terminal edges, thereby reducing the amount of ambiguity and thus the number of edges, since only edges with a validsemantic interpretation are ever introduced. |
| other,30-4-A92-1027,bq | </term> covers the longest possible <term> | span | </term> . This is facilitated through the | #17663 The resulting spanning edges are insured to be the correct ones by carefully controlling the order in which edges are introduced so that every final constituent covers the longest possiblespan. |
| other,2-4-A92-1027,bq | conventional treatments . The resulting <term> | spanning edges | </term> are insured to be the correct ones | #17635 The resultingspanning edges are insured to be the correct ones by carefully controlling the order in which edges are introduced so that every final constituent covers the longest possible span. |
| other,14-6-A92-1027,bq | using <term> semantic </term> rather than <term> | syntactic categories | </term> on the <term> terminal and non-terminal | #17717 A further reduction in the search space is achieved by using semantic rather thansyntactic categories on the terminal and non-terminal edges, thereby reducing the amount of ambiguity and thus the number of edges, since only edges with a valid semantic interpretation are ever introduced. |
| other,18-6-A92-1027,bq | <term> syntactic categories </term> on the <term> | terminal and non-terminal edges | </term> , thereby reducing the amount of <term> | #17721 A further reduction in the search space is achieved by using semantic rather than syntactic categories on theterminal and non-terminal edges, thereby reducing the amount of ambiguity and thus the number of edges, since only edges with a valid semantic interpretation are ever introduced. |
| other,37-1-A92-1027,bq | </term> are unknown and much of the <term> | text | </term> is irrelevant to the task . The <term> | #17580 We present an efficient algorithm for chart-based phrase structure parsing of natural language that is tailored to the problem of extracting specific information from unrestricted texts where many of the words are unknown and much of thetext is irrelevant to the task. |
| other,35-5-A92-1027,bq | be deduced despite the presence of <term> | unknown words | </term> . A further <term> reduction in the | #17700 This is facilitated through the use of phrase boundary heuristics based on the placement of function words, and by heuristic rules that permit certain kinds of phrases to be deduced despite the presence ofunknown words. |
| other,24-1-A92-1027,bq | extracting specific information from <term> | unrestricted texts | </term> where many of the <term> words </term> | #17567 We present an efficient algorithm for chart-based phrase structure parsing of natural language that is tailored to the problem of extracting specific information fromunrestricted texts where many of the words are unknown and much of the text is irrelevant to the task. |
| other,30-1-A92-1027,bq | unrestricted texts </term> where many of the <term> | words | </term> are unknown and much of the <term> | #17573 We present an efficient algorithm for chart-based phrase structure parsing of natural language that is tailored to the problem of extracting specific information from unrestricted texts where many of thewords are unknown and much of the text is irrelevant to the task. |
