论文信息 - Noun Phrase Recognition with Tree Patterns

Noun Phrase Recognition with Tree Patterns

This paper offers a method for the noun phrase recognition of Hungarian natural language texts based on machine learning methods. The approach learns noun phrase tree patterns described by regular expressions from an annotated corpus. The tree patterns are completed with probability values using error statistics. The noun phrase recognition parser tries to find the best-fitting trees for a sentence using backtracking technique. The results are used in an information extraction toolchain.

András Hócza | A. Hócza

[1] Beatrice Santorini,et al. Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[2] Steven Abney,et al. Parsing By Chunks , 1991 .

[3] János Csirik,et al. Manually annotated Hungarian corpus , 2003 .

[4] Atanas Kiryakov,et al. CLaRK - an XML-based System for Corpora Development 1 , 2001 .

[5] Shlomo Argamon,et al. A Memory-Based Approach to Learning Shallow Natural Language Patterns , 1999, COLING.

[6] Mitchell P. Marcus,et al. Text Chunking using Transformation-Based Learning , 1995, VLC@ACL.

[7] Shlomo Argamon,et al. A Memory-Based Approach to Learning Shallow Natural Language Patterns , 1998, ACL.

[8] Steven P. Abney. Partial parsing via finite-state cascades , 1996, Natural Language Engineering.

[9] Tamás Váradi,et al. Shallow parsing of Hungarian business news , 2003 .

[10] Tamás Váradi,et al. The Hungarian National Corpus , 2002, LREC.

[11] Stephen Muggleton,et al. Efficient Induction of Logic Programs , 1990, ALT.

[12] Erik F. Tjong Kim Sang,et al. Noun Phrase Recognition by System Combination , 2000, ANLP.

[13] Erik F. Tjong Kim Sang,et al. Representing Text Chunks , 1999, EACL.