String Segmentation Task
- It can be solved by a Sequence Segmentation System (that implements a Sequence Segmentation Algorithm).
- It can range from being a Data-Driven Sequence Segmentation Task (such as supervised sequence segmentation) to being a Heuristic Sequence Segmentation Task.
- a Text Tokenization Task.
- a Text Chunking Task, such as a Word Mention Segmentation Task, such as: WST("Famous notaries public include ex-attorney generals.") ⇒ ([Famous] [notaries public] [include] [ex-attorney generals]).
- an Allomorph Segmentation Task, such as: AST("Famous notaries public include ex-attorney generals.") ⇒
[?Famous] [notarie-] [-s] [public] [in-] [-clude] [ex-] [attorney] [general-] [-s].
- a Software Statement Tokenization Task, such as
x1=1.5; &rArr' [x1][=][1.5][;].
- a DNA Segmentation Task.
- See: CRF-based Sequence Segmentation Function.
- (Sarawagi, 2006) ⇒ Sunita Sarawagi. (2006). “Efficient Inference on Sequence Segmentation Models.” In: Proceedings of the 23rd International Conference on Machine Learning (ICML 2006). doi:10.1145/1143844.1143944
- (Sha & Pereira, 2003a) ⇒ Fei Sha, and Fernando Pereira. (2003). “Shallow Parsing with Conditional Random Fields.” In: Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology (HLT-NAACL 2003). doi:10.3115/1073445.1073473
- QUOTE:Sequence analysis tasks in language and biology are often described as mappings from input sequences to sequences of labels encoding the analysis. In language processing, examples of such tasks include part-of-speech tagging, named-entity recognition, and the task we shall focus on here, shallow parsing.