When Errors Become the Rule : Twenty Years with Transformation-Based Learning
Författare
Summary, in English
Transformation-based learning (TBL) is a machine learning method for, in particular, sequential classification, invented by Eric Brill [Brill 1993b, 1995a]. It is widely used within computational linguistics and natural language processing, but surprisingly little in other areas.
TBL is a simple yet flexible paradigm, which achieves competitive or even state-of-the-art performance in several areas and does not overtrain easily. It is especially successful at catching local, fixed-distance dependencies and seamlessly exploits information from heterogeneous discrete feature types. The learned representation—an ordered list of transformation rules—is compact and efficient, with clear semantics. Individual rules are interpretable and often meaningful to humans.
The present article offers a survey of the most important theoretical work on TBL, addressing a perceived gap in the literature. Because the method should be useful also outside the world of computational linguistics and natural language processing, a chief aim is to provide an informal but relatively comprehensive introduction, readable also by people coming from other specialities.
TBL is a simple yet flexible paradigm, which achieves competitive or even state-of-the-art performance in several areas and does not overtrain easily. It is especially successful at catching local, fixed-distance dependencies and seamlessly exploits information from heterogeneous discrete feature types. The learned representation—an ordered list of transformation rules—is compact and efficient, with clear semantics. Individual rules are interpretable and often meaningful to humans.
The present article offers a survey of the most important theoretical work on TBL, addressing a perceived gap in the literature. Because the method should be useful also outside the world of computational linguistics and natural language processing, a chief aim is to provide an informal but relatively comprehensive introduction, readable also by people coming from other specialities.
Avdelning/ar
Publiceringsår
2014
Språk
Engelska
Sidor
50-51
Publikation/Tidskrift/Serie
ACM Computing Surveys
Volym
46
Issue
4
Länkar
Dokumenttyp
Artikel i tidskrift
Förlag
Association for Computing Machinery (ACM)
Ämne
- General Language Studies and Linguistics
Nyckelord
- Artificial intelligence
- Knowledge Representation Formalisms and Methods
- Computational Linguistics
- Natural Language Processing
- Rule learning
Status
Published
ISBN/ISSN/Övrigt
- ISSN: 0360-0300