Automatic Functor Assignment AFA in the Prague Dependency Treebank

1
Automatic Functor Assignment (AFA) in the
Prague Dependency Treebank

• PDT
• a long term research project
• at the Institute of Formal and Applied
  Linguistics
• aimed at a complex annotation of a part of the
  Czech National Corpus
• annotation scheme - 3 levels

Raw text
AFAs position within the PDT
Morphologically tagged text
Analytic tree structures (ATS)
Tectogrammatical tree structures (TGTS)
2
Problem analysis, Data preprocessing

• Motivation
• to reduce the huge amount of human work involved
  in the development of the PDT
• Problem statement
• to assign a functor to every node in a TGTS
• Initial situation
• no AFA system with a reasonable cover existed
• human annotators use mostly only their language
  knowledge, not formal rules
• annotators take into account the whole-sentence
  context
• a certain amout of manually annotated TGTSs are
  available
• What is the minimal amount of information that is
  sufficient to decide about the functor ?
• Problem reformulation
• AFA ? to classify symbolic vectors into 53
  classes
• Available material - 18 files (up to 50 sentences
  in each)

vectors with 12 symbolic attributes
feature selection feature extraction

3
Components of the proposed AFA system

• Symbiosis of 4 different approaches
• 7 Rule-based Methods (RBMs)
• 3 Dictionary-based Methods (DBMs)
• Nearest vector (similarity)
• Machine learning (Quinlans C4.5, Sao Deroski)
• Implementation
• a set of small programs for preprocessing and
  format conversions, dictionary mining, functor
  assigning, and performance evaluation
• Linux filters, Perl, SQL
• assigners are applied in a strictly pipelined
  fashion
• Data Flow Diagram

4
Performance evaluation

• Detailed evaluation of several quantities for
  each assigner in a sequence
• Several sequences of assigners were tested
• e.g., a sequence of RBMs
• Comparison of different sequences of assigners

5
Further work

• Machine learning - searching for new regularities
• Improvement of dictionaries
• Tectogrammatical annotation of verb valency
  frames
• Categorial grammars

Talks Publications
language ? ? fuzzy sets
Z Fuzzy ontroller as a Tool for Traffic
Simulation. Mendel 1999
Z Introduction to the PDT, Faculty of Arts,
Ljubljana, 2000
Z Constrained Fuzzy Arithmetic Engineers
View. CMP Research Rep.
Z AFA in the PDT, seminar at the IFAL, 2000
Z AFA in the PDT, TSD 2000
Z Comp. Problems of CFA,CMP seminar
S. Deroski, Z ML approach to AFA in the PDT,
5th TELRI seminar, 2000
M. Navara, Z Comp. Problems of CFA, ISCI 2000
?
S. Deroski, Z ML approach to AFA in the PDT,
ACL, 2001
M. Navara, Z How to make CFA efficient, Soft
Computing 2001
Stranáková, Skoumalová, Panevová, Z Tectogram.
annotation of verb. val. frames, TSD 2001
?
M. de Cock, Z Representing Ling. Hedges by
L-Fuzzy Modifiers, CIMCA 2001
?