Some Languages Seem Easier to Parse Because Their Treebanks Leak
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Some Languages Seem Easier to Parse Because Their Treebanks Leak. / Søgaard, Anders.
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, 2020. p. 2765–2770.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Some Languages Seem Easier to Parse Because Their Treebanks Leak
AU - Søgaard, Anders
PY - 2020
Y1 - 2020
N2 - Cross-language differences in (universal) dependency parsing performance are mostly attributed to treebank size, average sentence length, average dependency length, morphological complexity, and domain differences. We point at a factor not previously discussed: If we abstract away from words and dependency labels, how many graphs in the test data were seen in the training data? We compute graph isomorphisms, and show that, treebank size aside, overlap between training and test graphs explain more of the observed variation than standard explanations such as the above.
AB - Cross-language differences in (universal) dependency parsing performance are mostly attributed to treebank size, average sentence length, average dependency length, morphological complexity, and domain differences. We point at a factor not previously discussed: If we abstract away from words and dependency labels, how many graphs in the test data were seen in the training data? We compute graph isomorphisms, and show that, treebank size aside, overlap between training and test graphs explain more of the observed variation than standard explanations such as the above.
U2 - 10.18653/v1/2020.emnlp-main.220
DO - 10.18653/v1/2020.emnlp-main.220
M3 - Article in proceedings
SP - 2765
EP - 2770
BT - Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
PB - Association for Computational Linguistics
T2 - The 2020 Conference on Empirical Methods in Natural Language Processing
Y2 - 16 November 2020 through 20 November 2020
ER -
ID: 258390141