Add documentation on the data frames returned
Change-Id: Ifdc9b27829c6ab01aa4d6d7b88c339884a470877
diff --git a/man/collocationScores.Rd b/man/collocationScores.Rd
index b206e18..4221d25 100644
--- a/man/collocationScores.Rd
+++ b/man/collocationScores.Rd
@@ -2,7 +2,7 @@
% Please edit documentation in R/derekovecs.R
\name{collocationScores}
\alias{collocationScores}
-\title{collocationScores}
+\title{Get collocation scores}
\usage{
collocationScores(w, c, ...)
}
@@ -15,7 +15,36 @@
}
\value{
A one row data frame with collocate and its association scores.
+\describe{
+\item{word}{collocate}
+\item{f2}{abs. frequency of collocate}
+\item{f}{abs. frequency of collocation}
+\item{npmi}{normalized pmi (Bouma 2009)}
+\item{pmi}{pointwise mutual information}
+\item{dice}{dice score}
+\item{ld}{log-dice score (Rychlý 2008) for whole window}
+\item{lfmd}{log-frequency biased mutual dependency ≙ pmi³ (Dalle 1994; Thanopoulos et al. 2002)}
+\item{llr}{log-likelihood (Dunning 1993; Evert 2004)}
+\item{ln_count}{frequency of collocate as left neighbour of node}
+\item{ln_pmi}{pmi as left neighbour}
+\item{md}{mutual dependency ≙ pmi² (Dalle 1994; Thanopoulos et al. 2002)}
+\item{rn_count}{frequency of collocate as right neighbour of node}
+\item{rn_pmi}{pmi as right neighbour}
+\item{ldaf}{log-dice score for auto focus window}
+\item{win}{binary encoded positions at which the collocate appears at least once, e.g.: 1023 = 2^10-1 ≙ 11111 node 11111}
+\item{afwin}{binary encoded auto-focus window (see Perkuhn et al. 2012: E8-15), e.g. 64 = 2^6 ≙ 00010 node 00000 (Aus gutem Grund)}
+}
}
\description{
Calculate the association scores between a node (target word) and words in a window around the it.
}
+\references{
+Daille, B. (1994): Approche mixte pour l’extraction automatique de terminologie: statistiques lexicales et filtres linguistiques. PhD thesis, Université Paris 7.
+
+Dunning, T. (1993): Accurate methods for the statistics of surprise and coincidence. Comput. Linguist. 19, 1 (March 1993), 61-74.
+
+Evert, Stefan (2004): The Statistics of Word Cooccurrences: Word Pairs and Collocations. PhD dissertation, IMS, University of Stuttgart. Published in 2005, URN urn:nbn:de:bsz:93-opus-23714.
+Free PDF available from \url{https://purl.org/stefan.evert/PUB/Evert2004phd.pdf}
+
+Thanopoulos, A., Fakotakis, N., Kokkinakis, G. (2002): Comparative evaluation of collocation extraction metrics. In: Proc. of LREC 2002: 620–625.
+}
diff --git a/man/cosineSimilarity.Rd b/man/cosineSimilarity.Rd
index 5b30c89..f942028 100644
--- a/man/cosineSimilarity.Rd
+++ b/man/cosineSimilarity.Rd
@@ -2,7 +2,7 @@
% Please edit documentation in R/derekovecs.R
\name{cosineSimilarity}
\alias{cosineSimilarity}
-\title{cosineSimilarity}
+\title{Get cosine similarity}
\usage{
cosineSimilarity(w1, w2, ...)
}
diff --git a/man/countbasedCollocates.Rd b/man/countbasedCollocates.Rd
index c3f153f..33fd248 100644
--- a/man/countbasedCollocates.Rd
+++ b/man/countbasedCollocates.Rd
@@ -2,7 +2,7 @@
% Please edit documentation in R/derekovecs.R
\name{countbasedCollocates}
\alias{countbasedCollocates}
-\title{countbasedCollocates}
+\title{Get count-based collocates}
\usage{
countbasedCollocates(w = "Test", ...)
}
@@ -12,8 +12,11 @@
\item{...}{Additional parameters to pass to the API.}
}
\value{
-A data fram with the most salient collcates and their association scores.
+A data frame with the most salient collocates and their association scores.
}
\description{
Get the collocates of a word in the count-based dereko model.
}
+\seealso{
+\code{\link[=collocationScores]{collocationScores()}} for details
+}
diff --git a/man/derekovecsServer.Rd b/man/derekovecsServer.Rd
index 4ef9089..cac1cb1 100644
--- a/man/derekovecsServer.Rd
+++ b/man/derekovecsServer.Rd
@@ -2,7 +2,7 @@
% Please edit documentation in R/derekovecs.R
\name{derekovecsServer}
\alias{derekovecsServer}
-\title{DeReKoVecsServer}
+\title{Get the DeReKoVecs server}
\usage{
derekovecsServer()
}
@@ -10,5 +10,5 @@
The URL of the DeReKoVecs API server.
}
\description{
-DeReKoVecsServer
+Get the DeReKoVecs server
}
diff --git a/man/paradigmaticNeighbours.Rd b/man/paradigmaticNeighbours.Rd
index 225dae7..cdbf0a2 100644
--- a/man/paradigmaticNeighbours.Rd
+++ b/man/paradigmaticNeighbours.Rd
@@ -2,7 +2,7 @@
% Please edit documentation in R/derekovecs.R
\name{paradigmaticNeighbours}
\alias{paradigmaticNeighbours}
-\title{paradigmaticNeighbours}
+\title{Get paradigmatic neighbours}
\usage{
paradigmaticNeighbours(word = "Test", ...)
}
diff --git a/man/syntagmaticNeighbours.Rd b/man/syntagmaticNeighbours.Rd
index 6278606..e84038f 100644
--- a/man/syntagmaticNeighbours.Rd
+++ b/man/syntagmaticNeighbours.Rd
@@ -2,7 +2,7 @@
% Please edit documentation in R/derekovecs.R
\name{syntagmaticNeighbours}
\alias{syntagmaticNeighbours}
-\title{syntagmaticNeighbours}
+\title{Get syntagmatic neighbours}
\usage{
syntagmaticNeighbours(word = "Test", ...)
}
@@ -12,8 +12,18 @@
\item{...}{Additional parameters to pass to the API.}
}
\value{
-Data frame syntagmatic neighbours of a word from the predictive derekovecs model.
+Data frame with the syntagmatic neighbours of a node predicted from derekovecs model, with the following columns:
+
+\describe{
+\item{average}{⟨a⟩ - Average raw activation of the collocator in the columns selected by auto-focus.}
+\item{heat}{Vector of activation of the respective collocator in the slots around the target normalized by its maximum.}
+\item{max}{max(a) - Maximum activation of the collocator anywhere in the output layer.}
+\item{overall}{Σa/Σw – Sum of the activations over the whole window normalized by the total window sum (no auto-focus).}
+\item{pos}{Binary encoded position of where in the window around the node the collocate is predecited with above 0 probability, e.g. 64 = 2^6 ≙ 00010 node 00000}
+\item{rank}{Frequency rank of predicted collocate}
+\item{word}{Predicted collocate}
+}
}
\description{
-Get the syntagmatic neighbours of a word from the predictive derekovecs model.
+Get the syntagmatic neighbour predictions of a word from the DeReKoVecs model (see Fankhauser/Kupietz 2022, 2017).
}