- All Implemented Interfaces:
public class XSqrA_M extends WeightingModelThis class implements the XSqrA_M weighting model, which computed the inner product of Pearson's X^2 with the information growth computed with the multinomial M. It is an unsupervised DFR model of IR (free from parameters), which can be used on short or medium verbose queries.
XSqrA_M has a high performance, and in particular has statistically significant better MAP performance than all other supervised models on the GOV2 collection. MAP for short (title only) and medium (title+description) topics, and comparative p values (two-tailed paired t-test) compared to supervised models (with optimal MAP parameter values) are as follows:
Queries MAP of XSqrA_M LGD Dirichlet_LM PL2 BM25 In_expB2 short 0.3156 p=0.3277 p=0.0075 p=0.0055 p=0.0064 p=0.0002 medium 0.3311 p=2.3E-07 p=0.0002 p=0.0395 p=0.0025 p=2.4E-10
References Frequentist and Bayesian approach to Information Retrieval. G. Amati. In Proceedings of the 28th European Conference on IR Research (ECIR 2006). LNCS vol 3936, pages 13--24.
- Gianni Amati
- See Also:
- Serialized Form
Constructors Constructor Description
XSqrA_M()A default constructor to make this model.
All Methods Instance Methods Concrete Methods Modifier and Type Method Description
getInfo()Returns the name of the model, in this case "XSqrA_M"
score(double tf, double docLength)Uses XSqrA_M to compute a weight for a term in a document.
Methods inherited from class org.terrier.matching.models.WeightingModel
clone, getOverflowed, getParameter, prepare, score, setCollectionStatistics, setEntryStatistics, setKeyFrequency, setParameter, setRequest
public final java.lang.String getInfo()Returns the name of the model, in this case "XSqrA_M"
public final double score(double tf, double docLength)Uses XSqrA_M to compute a weight for a term in a document.