Doc: ROUGE: docs updates

Project.toml

@@ -7,6 +7,7 @@ version = "0.7.5"
 [deps]
 DataStructures = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
 DelimitedFiles = "8bb1440f-4735-579b-a4ab-409b98df4dab"
+DocStringExtensions = "ffbed154-4ef7-542d-bbb7-c09d3a79fcae"
 JSON = "682c06a0-de6a-54ab-a142-c8b1cf79cde6"
 Languages = "8ef0a80b-9436-5d2c-a485-80b904378c43"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
@@ -24,6 +25,7 @@ WordTokenizers = "796a5d58-b03d-544a-977e-18100b691f6e"
 [compat]
 DataStructures = "0.17, 0.18"
 DelimitedFiles = "1"
+DocStringExtensions = "0.9"
 JSON = "0.21"
 Languages = "0.4"
 ProgressMeter = "1.5"

docs/src/evaluation_metrics.md

@@ -8,36 +8,28 @@ As of now TextAnalysis provides the following evaluation metrics.
 
 * [BLEU (bilingual evaluation understudy)](https://en.wikipedia.org/wiki/BLEU)
 
-## ROUGE-N
+## ROUGE-N, ROUGE-L, ROUGE-L-Summary
 This metric evaluation based on the overlap of N-grams
 between the system and reference summaries.
 
 ```@docs
+argmax
+average
 rouge_n
+rouge_l_sentence
+rouge_l_summary
 ```
 
-The function takes the following arguments -
-
-* `references::Array{T} where T<: AbstractString` = The list of reference summaries.
-* `candidate::AbstractString` = Input candidate summary, to be scored against reference summaries.
-* `n::Integer` = Order of NGrams
-* `avg::Bool` = Setting this parameter to `true`, applies jackkniving the calculated scores. Defaults to `true`
-* `lang::Language` = Language of the text, useful while generating N-grams. Defaults to English i.e. Languages.English()
-
-```julia
-julia> candidate_summary =  "Brazil, Russia, China and India are growing nations. They are all an important part of BRIC as well as regular part of G20 summits."
-"Brazil, Russia, China and India are growing nations. They are all an important part of BRIC as well as regular part of G20 summits."
-
-julia> reference_summaries = ["Brazil, Russia, India and China are the next big political powers in the global economy. Together referred to as BRIC(S) along with South Korea.", "Brazil, Russia, India and China are together known as the  BRIC(S) and have been invited to the G20 summit."]
-2-element Array{String,1}:
- "Brazil, Russia, India and China are the next big political powers in the global economy. Together referred to as BRIC(S) along with South Korea."
- "Brazil, Russia, India and China are together known as the  BRIC(S) and have been invited to the G20 summit."                                    
+```@example
+using TextAnalysis
 
-julia> rouge_n(reference_summaries, candidate_summary, 2, avg=true)
-0.1317241379310345
+candidate_summary =  "Brazil, Russia, China and India are growing nations. They are all an important part of BRIC as well as regular part of G20 summits."
+reference_summaries = ["Brazil, Russia, India and China are the next big political powers in the global economy. Together referred to as BRIC(S) along with South Korea.", "Brazil, Russia, India and China are together known as the  BRIC(S) and have been invited to the G20 summit."]
 
-julia> rouge_n(reference_summaries, candidate_summary, 1, avg=true)
-0.5051282051282051
+results = [
+    rouge_n(reference_summaries, candidate_summary, 2),
+    rouge_n(reference_summaries, candidate_summary, 1)
+] .|> argmax
 ```
 
 ## BLEU (bilingual evaluation understudy)

src/TextAnalysis.jl

@@ -12,6 +12,7 @@ module TextAnalysis
     using Statistics
     using Serialization
     using ProgressMeter
+    using DocStringExtensions
 
     import Base: depwarn, merge!
     import Serialization: serialize, deserialize