Báo cáo khoa học: "An Improved Parser for Data-Oriented Lexical-Functional Analysis"

We present an LFG-DOP parser which uses fragments from LFG-annotated sentences to parse new sentences. Experiments with the Verbmobil and Homecentre corpora show that (1) Viterbi n best search performs about 100 times faster than Monte Carlo search while both achieve the same accuracy; (2) the DOP hypothesis which states that parse accuracy increases with increasing fragment size is confirmed for LFG-DOP; (3) LFGDOP's relative frequency estimator performs worse than a discounted frequency estimator; and (4) LFG-DOP significantly outperforms TreeDOP if evaluated on tree structures only. (Neumann & Flickinger 1999), and Montague Grammar (Bonnema et al. 1997; Bod 1999)

Bấm vào đây để xem trước nội dung
120    10    1    21-06-2021
17    8    1    21-06-2021