Đang chuẩn bị liên kết để tải về tài liệu:
Báo cáo khoa học: "Experience with an Easily Computed Metric for Ranking Alternative Parses"

This brief paper, which is itself an extended abstract for a forthcoming paper, describes a metric that can be easily computed during either b o t t o m - u p or top-down construction of a parse tree for ranking the desirability of alternative parses. In its simplest form, the metric tends to p r e f e r trees in which constituents are pushed as far down a s possible, but by appropriate modification of a c o n s t a n t in the formula other behavior can be obtained also. This paper includes an. | Experience with an Easily Computed Metric for Ranking Alternative Parses George E. Heidorn Computer Sciences Department IBM Thomas J. Watson Research Center Yorktown Heights New York 10598 Abstract This brief paper which is itself an extended abstract for a forthcoming paper describes a metric that can be easily computed during either bottom-up or top-down construction of a parse tree for ranking the desirability of alternative parses. In its simplest form the metric tends to prefer trees in which constituents are pushed as far down as possible but by appropriate modification of a constant in the formula other behavior can be obtained also. This paper includes an introduction to the EPISTLE system being developed at IBM Research and a discussion of the results of using this metric with that system. Introduction Heidorn 1976 described a technique for computing a number for each node during the bottom-up construction of a parse tree such that a node with a smaller number is to be preferred to a node with a larger number covering the same portion of text. At the time this scheme was used primarily to select among competing noun phrases in queries to a program explanation system. Although it appeared to work well it was not extensively tested. Recently as part of our research on the EPISTLE system this idea has been modified and extended to work over entire sentences and to provide for top-down computation. Also we have done an analysis of 80 sentences with multiple parses from our data base to evaluate the performance of this metric and have found that it is producing very good results. This brief paper which is actually an extended abstract for a forthcoming paper begins with an introduction to the EPISTLE system to set the stage for the current application of this metric. Then the metric s computation is described followed by a discussion of the results of the 80-sentence analysis. Finally some comparisons are made to related work by others. The EPISTLE System In .