Abstract | ||
---|---|---|
We present a novel ensemble of six methods for improving the efficiency of chart realization. The methods are couched in the framework of Combinatory Categorial Grammar (CCG), but we conjecture that they can be adapted to related grammatical frameworks as well. The ensemble includes two new methods introduced here-feature-based licensing and instantiation of edges, and caching of category combinations-in addition to four previously introduced methods-index filtering, LF chunking, edge pruning based on n-gram scores, and anytime search. We compare the relative contributions of each method using two test grammars, and show that the methods work best in combination. Our evaluation also indicates that despite the exponential worst-case complexity of the basic algorithm, the methods together can constrain the realization problem sufficiently to meet the interactive needs of natural language dialogue systems. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1007/978-3-540-27823-8_19 | Lecture Notes in Artificial Intelligence |
Keywords | Field | DocType |
combinatory categorial grammar,indexation | Rule-based machine translation,Test suite,Computer science,Machine translation,Natural language,Combinatory categorial grammar,Artificial intelligence,Natural language processing,Categorial grammar,Chart,Chunking (psychology) | Conference |
Volume | ISSN | Citations |
3123 | 0302-9743 | 34 |
PageRank | References | Authors |
1.96 | 13 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael White | 1 | 51 | 8.25 |