Dependency Parsing with Reference to Slovene, Spanish and Swedish

1
Dependency Parsing with Reference to Slovene,
Spanish and Swedish

• Simon Corston-Oliver
• Anthony Aue
• Microsoft Research

2
Noteworthy results

• Slovene
• Labeled DA 72.42 (second)
• Not significantly different from 1 (73.44)
• Swedish
• 1 for unlabeled DA (89.54)
• Much worse than 3 for labeled DA(79.69 vs
  82.31)

3
Outline

• Two stage pipeline
• Identify unlabeled directed dependencies
• Label the dependencies

4
Parser

• Unlabeled directed dependencies
• Discriminatively trained linear classifier
• Projective dependencies only
• Parse features
• Case-normalized surface form and lemma
• POS of each token
• POS of intervening and neighboring tokens
• Combinations of these
• Direction and distance of attachment

5
POS features

• Use fine POS tags for all languages except Dutch
  and Turkish
• Swedish Normalize tags for auxiliaries
• Orig vara (be) AV måst (must) MV
• Replace with aux
• Unlabeled DA 89.23 ? 89.45

6
Root identification features

• Many errors identifying root in periphrastic
  constructions with aux and participle
• E.g. German aux/modal in second position in
  declarative main clause
• initial with subj-aux inversion
• New features
• POS sequence to left of each token
• Leftmost finite verb and not preceded by
  subordinating conj or relative pron
• Sentence does (not) contain finite verb

7
Root identification features

• Danish improved
• RA 94.12 ? 94.72
• Spanish improved
• RA 80.08 ? 83.57

8
Labeling dependencies

• Use a maximum entropy classifier (Berger et al
  1996)
• Fast to train
• Good probability estimates
• Intended to jointly model sets of labels
• Actually labeled independently
• Better results with SVM?

9
Swedish using SVMs
10
Japanese using SVMs
11
Conclusion

• Two stage pipeline
• Feature engineering important
• For predicting dependencies
• For labeling dependencies
• Replacing maxent classifier with SVM gave boost