[PDF][PDF] Hybrid text chunking
Fourth Conference on Computational Natural Language Learning and the …, 2000•aclanthology.org
This paper proposes an error-driven HMM-based text chunk tagger with context-dependent
lexicon. Compared with standard HMM-based tagger, this tagger incorporates more
contextual information into a lexical entry. Moreover, an error-driven learning approach is
adopted to decrease the memory requirement by keeping only positive lexical entries and
makes it possible to further incorporate more context-dependent lexical entries. Finally,
memory-based learning is adopted to further improve the performance of the chunk tagger.
lexicon. Compared with standard HMM-based tagger, this tagger incorporates more
contextual information into a lexical entry. Moreover, an error-driven learning approach is
adopted to decrease the memory requirement by keeping only positive lexical entries and
makes it possible to further incorporate more context-dependent lexical entries. Finally,
memory-based learning is adopted to further improve the performance of the chunk tagger.
Abstract
This paper proposes an error-driven HMM-based text chunk tagger with context-dependent lexicon. Compared with standard HMM-based tagger, this tagger incorporates more contextual information into a lexical entry. Moreover, an error-driven learning approach is adopted to decrease the memory requirement by keeping only positive lexical entries and makes it possible to further incorporate more context-dependent lexical entries. Finally, memory-based learning is adopted to further improve the performance of the chunk tagger.
aclanthology.org