Co-Occurrence Statistic
(Redirected from distributional statistics)
Jump to navigation
Jump to search
A Co-Occurrence Statistic is a statistic function for some co-occurrence relation (where two items occur together within some composite data item).
- AKA: Distributional Statistic, Co-occur.
- Context:
- It can range from being a Local Co-occurrence Statistic to being a Global Co-occurrence Statistic.
- It can range from being a Linguistic Co-occurrence Statistic (such as lexical co-occurrence) to being a Visual Pattern Co-occurrence Statistic.
- It can be referenced by a Co-Occurrence Pattern.
- It can be related to a: Mutual Information Test, a Dice Coefficient, χ2 Test, a LSA-based Statistic Function, ...
- Example(s):
- Counter-Example(s):
- See: Co-Occurrence Matrix, n-Gram Co-Occurrence Statistic, Term Co-occurrence Function, Co-occur Relation, Occurrence.
References
2010
- (Ladicky et al., 2010) ⇒ Lubor Ladicky, Chris Russell, Pushmeet Kohli, and Philip HS Torr. (2010). “Graph Cut based Inference with Co-occurrence Statistics.” In: Computer Vision – ECCV 2010.
- QUOTE: … Conditional random fields (crfs) used in computer vision typically model only local interactions between variables, … Here the aim is to assign a label to each pixel of a given image from a set of possible object classes. … use random fields to model local interactions between pixels or super-pixels. One of the cues that helps recognition is global object co-occurrence statistics, a measure of which classes (such as chair or motorbike) are likely to occur in the same image together. …
2009
- (WordNet, 2009) ⇒ http://wordnetweb.princeton.edu/perl/webwn?s=co-occurrence
- S: (n) accompaniment, concomitant, attendant, co-occurrence (an event or situation that happens at the same time as or in connection with another)
- S: (n) concurrence, coincidence, conjunction, co-occurrence (the temporal property of two things happening at the same time) "the interval determining the coincidence gate is adjustable"
2001
- (Jacquemin, 2001) ⇒ Christian Jacquemin. (2001). “Spotting and Discovering Terms Through Natural Language Processing." MIT Press. ISBN:0262100851
- QUOTE: A statistical measure of co-occurrence is a statistical measure of the co-occurrences of two or more words in a fixed-length text window..