Search papers, labs, and topics across Lattice.
Affiliation:
3
0
1
0
Parsing Korean requires a nuanced approach, as fine-grained morphological details significantly enhance accuracy over simpler representations.
Despite superior head prediction accuracy, learned heads fail to consistently improve constituency parsing, especially when evaluated on punctuation, challenging the assumption that better headedness directly translates to better parsing.
Learning constituent headedness as a supervised task achieves near-ceiling accuracy and significantly boosts constituency-to-dependency conversion compared to traditional rule-based approaches.
