Calculating the Optimal Step in Shift-Reduce Dependency Parsing: From Cubic to Linear Time
2019 ◽
Vol 7
◽
pp. 283-296
Keyword(s):
We present a new cubic-time algorithm to calculate the optimal next step in shift-reduce dependency parsing, relative to ground truth, commonly referred to as dynamic oracle. Unlike existing algorithms, it is applicable if the training corpus contains non-projective structures. We then show that for a projective training corpus, the time complexity can be improved from cubic to linear.
2020 ◽
Vol 34
(05)
◽
pp. 8319-8326
Keyword(s):
Keyword(s):
2000 ◽
Vol 11
(03)
◽
pp. 365-371
◽
Keyword(s):