Language Independent Probabilistic Context-Free Parsing Bolstered - - PowerPoint PPT Presentation

▶

Feb 26, 2024 271 likes •356 views

Language Independent Probabilistic Context-Free Parsing Bolstered by Machine Learning Michael Schiehlen & Kristina Spranger Institut f ur Maschinelle Sprachverarbeitung Universit at Stuttgart Language Independent Probabilistic

SLIDE 1

Language Independent Probabilistic Context-Free Parsing Bolstered by Machine Learning

Michael Schiehlen & Kristina Spranger Institut f¨ ur Maschinelle Sprachverarbeitung Universit¨ at Stuttgart

Language Independent Probabilistic Context-Free Parsing Bolstered by Machine Learning – p.1/7

SLIDE 2

Outline

General approach: convert dependency structure to constituency structure and use plain PCFG insert information on subcategorisation into the grammar (automatically from dependency relations) which names for phrasal categories?

Language Independent Probabilistic Context-Free Parsing Bolstered by Machine Learning – p.2/7

SLIDE 3

From Dep. to Const. Structure

ROOT.P ROOT.P ROOT.P pc.P su.P

bj1.P

det su R

su,vc

✁

vc KON R

✁

det mod

Haar neus werd platgedrukt en leek

een jonge champignon det su cnj det mod vc

pc cnj

Language Independent Probabilistic Context-Free Parsing Bolstered by Machine Learning – p.3/7

SLIDE 4

Performance in CONLL

AR CH CZ DA DU GE JA PO SL SP SW TU

Language Independent Probabilistic Context-Free Parsing Bolstered by Machine Learning – p.4/7

SLIDE 5

Improvements after Submission

Markovization of PCFG rules (minor improvements) language-dependent manual determination of phrasal categories for Chinese, Czech, German, Slovene, Spanish (major improvements)

Language Independent Probabilistic Context-Free Parsing Bolstered by Machine Learning – p.5/7

SLIDE 6

Tagging Approach

Dependency Parsing as Tagging: use MaxEnt-tagger to assign head–relation pairs to individual tokens heads in ‘nth-tag’ representation, e.g.

for the last token with POS tag

✁ ✁

for the second to the right Combination of PCFG-Parsing and Tagging: use parser output as an additional feature

Language Independent Probabilistic Context-Free Parsing Bolstered by Machine Learning – p.6/7

SLIDE 7

Performance of Combination

AR CH CZ DA DU GE JA PO SL SP SW TU

Language Independent Probabilistic Context-Free Parsing Bolstered by Machine Learning – p.7/7