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
- 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.
- Klein & Manning, 2003, Accurate Unlexicalized Parsing (Proceedings of the 41st Annual Meeting of ACL), §4, pp. 427–428
- 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”.
- Klein & Manning, 2003, Accurate Unlexicalized Parsing (Proceedings of the 41st Annual Meeting of ACL), §4, pp. 427–428
- 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.
- Klein & Manning, 2003, Accurate Unlexicalized Parsing (Proceedings of the 41st Annual Meeting of ACL), §4, pp. 427–428
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/