From ea008b9238474185b7ab1c39f567b1f3c0bfd891 Mon Sep 17 00:00:00 2001
From: Aurelien FOUCRET <aurelien.foucret@elastic.co>
Date: Mon, 11 Mar 2024 16:21:11 +0100
Subject: [PATCH] Apply suggestions from review.

---
 .../learning-to-rank-model-training.asciidoc                | 6 ++++--
 .../search-your-data/learning-to-rank-search-usage.asciidoc | 2 +-
 .../search/search-your-data/learning-to-rank.asciidoc       | 4 ++--
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/docs/reference/search/search-your-data/learning-to-rank-model-training.asciidoc b/docs/reference/search/search-your-data/learning-to-rank-model-training.asciidoc
index 6122aad7e1699..fb026578bc00d 100644
--- a/docs/reference/search/search-your-data/learning-to-rank-model-training.asciidoc
+++ b/docs/reference/search/search-your-data/learning-to-rank-model-training.asciidoc
@@ -45,7 +45,8 @@ feature_extractors=[
         feature_name="title_bm25",
         query={"match": {"title": "{{query}}"}}
     ),
-    # We can use a script_score query to get the value of the field rating directly as a feature:
+    # We can use a script_score query to get the value
+    # of the field rating directly as a feature:
     QueryFeatureExtractor(
         feature_name="popularity",
         query={
@@ -55,7 +56,8 @@ feature_extractors=[
             }
         },
     ),
-    # We can execute a script on the value of the query and use the return value as a feature:
+    # We can execute a script on the value of the query
+    # and use the return value as a feature:
     QueryFeatureExtractor(
         feature_name="query_length",
         query={
diff --git a/docs/reference/search/search-your-data/learning-to-rank-search-usage.asciidoc b/docs/reference/search/search-your-data/learning-to-rank-search-usage.asciidoc
index e4497bd3211c1..1d040a116ad9a 100644
--- a/docs/reference/search/search-your-data/learning-to-rank-search-usage.asciidoc
+++ b/docs/reference/search/search-your-data/learning-to-rank-search-usage.asciidoc
@@ -13,7 +13,7 @@ For more information, see {subscriptions}.
 [[learning-to-rank-rescorer]]
 ==== Learning To Rank as a rescorer
 
-Once your LTR model is trained and deployed in {es}, it can be used as a <<rescore, rescorer>> in the <<search-your-data, Search API>>:
+Once your LTR model is trained and deployed in {es}, it can be used as a <<rescore, rescorer>> in the <<search-your-data, search API>>:
 
 [source,console]
 ----
diff --git a/docs/reference/search/search-your-data/learning-to-rank.asciidoc b/docs/reference/search/search-your-data/learning-to-rank.asciidoc
index 8af8a56e77526..08fad9db9c0f6 100644
--- a/docs/reference/search/search-your-data/learning-to-rank.asciidoc
+++ b/docs/reference/search/search-your-data/learning-to-rank.asciidoc
@@ -109,11 +109,11 @@ The heart of LTR is of course an ML model. A model is trained using the training
 
 The LTR space is evolving rapidly and many approaches and model types are being
 experimented with. In practice {es} relies specifically on gradient boosted decision tree
-(GBDT) models for LTR inference.
+(https://en.wikipedia.org/wiki/Gradient_boosting#Gradient_tree_boosting[GBDT^]) models for LTR inference.
 
 Note that {es} supports model inference but the training process itself must
 happen outside of {es}, using a GBDT model. Among the most popular LTR models
-used today, LambdaMART provides strong ranking performance with low inference
+used today, https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/MSR-TR-2010-82.pdf[LambdaMART^] provides strong ranking performance with low inference
 latencies. It relies on GBDT models and is therefore a perfect fit for LTR in
 {es}.