Accurate Unlexicalized Parsing

Klein & Manning, 2003, Accurate Unlexicalized Parsing (Proceedings of the 41st Annual Meeting of ACL)

Subscriber deck — free during early access

3 cards in “4 Tag Splitting” · whole deck

4 Tag Splitting

  1. What is TAG-PA, and why does it help?
    Parent annotation of preterminal tags, the best single annotation (+2.52 F1 alone). Tags in non-canonical positions behave differently: the most common adverbs under ADVP are also and now, under VP n’t and not, under NP only and just.
  2. Why split the IN tag, and how?
    IN conflates subordinating conjunctions (while, if), complementizers (that, for) and prepositions (of, in), which TAG-PA only partly separates. SPLIT-IN is a linguistically motivated 6-way split, e.g. letting if prefer S complements in “to see if advertising works”.
  3. Which lexeme-specific tag splits did Klein and Manning use?
    SPLIT-AUX marks all forms of be and have; SPLIT-CC marks but and &, which behave unlike other conjunctions; and % gets its own tag, like $. Together they reached 81.81 F1.

Source

  • Dan Klein and Christopher D. Manning. 2003. Accurate Unlexicalized Parsing. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pp. 423–430. https://aclanthology.org/P03-1054/