Supervised String Segmentation Task

Context:
- It can produce a Sequence Segmentation Function (that makes use of sequence segmentation features).
- It can be solved by a Supervised String Segmentation System (that implements a Supervised String Segmentation Algorithm).
Example(s):
- a Supervised Text Segmentation Task.
- a Supervised DNA Segmentation Task.
- …
Counter-Example(s):
- a Supervised Sequence Tagging Task.
- a Supervised Information Extraction Task.
See: Sequence Segmentation Statistical Models.

References

(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
- Given an input sequence x = x₁, ..., x_n, a segmentation s of x consists of a sequence of variable length segments s = s₁, ..., s_p where each segment s_j = <t_j, u_j, y_j> consists of a start position t_j, an end position u_j, and a label y_j ∈ [math]\displaystyle{ Y }[/math] . Conceptually, a segment means that the tag y_j is given to all x_i’s between [math]\displaystyle{ i }[/math] = t_j and [math]\displaystyle{ i }[/math] = u_j, inclusive. Each segment s_j can be associated with a vector of features that captures the dependence of its label on input properties in the neighborhood of the segment and the label of the segment before it. 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.

(Keshet et al., 2005) ⇒ J. Keshet, B. Shalev-Shwartz, and Yoram Singer. (2005). “Phoneme alignment using large margin techniques.” In: Proceedings of the NIPS 2005 Workshop on the Advances in Structured Learning for Text and Speech Processing.
(McDonald et al., 2005) ⇒ Ryan T. McDonald, Koby Crammer, and Fernando Pereira. (2005). “Flexible Text Segmentation with Structured Multilabel Classification.” In: Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing (HLT/EMNLP, 2005).