Sequence Segmenting Function
(Redirected from Chunking Function)
Jump to navigation
Jump to search
A Sequence Segmenting Function is a segmentation function that can accept a string (an solve a string segmentation task/chunking task).
- AKA: String Segmentation Function, Chunking Function.
- Context:
- It can be based on a Sequence Tagging Function (that makes use of string tagging features).
- It can be associated with a Sequence Confidence Score Function.
- Example(s):
- Counter-Example(s):
- See: Segmentation Function, String, Predicted String Segment, String Segmentation Algorithm, Sequence Segmentation Statistical Models, Supervised Sequence Segmentation Task.
References
2006
- (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
- … The goal during inference is to simultaneously find a segmentation of the input sequence and label each segment so as to maximize the total score over all segments.