1.0Aeologic Bloghttps://www.aeologic.com/blogrich600338<blockquote class="wp-embedded-content" data-secret="VS6DI2fJ7w"><a href="https://www.aeologic.com/blog/learning-to-rank18-learning-to-rank/">Learning To Rank – Ultimate Solr Guide</a></blockquote><iframe sandbox="allow-scripts" security="restricted" src="https://www.aeologic.com/blog/learning-to-rank18-learning-to-rank/embed/#?secret=VS6DI2fJ7w" width="600" height="338" title="“Learning To Rank – Ultimate Solr Guide” — Aeologic Blog" data-secret="VS6DI2fJ7w" frameborder="0" marginwidth="0" marginheight="0" scrolling="no" class="wp-embedded-content"></iframe><script> /*! This file is auto-generated */ !function(d,l){"use strict";l.querySelector&&d.addEventListener&&"undefined"!=typeof URL&&(d.wp=d.wp||{},d.wp.receiveEmbedMessage||(d.wp.receiveEmbedMessage=function(e){var t=e.data;if((t||t.secret||t.message||t.value)&&!/[^a-zA-Z0-9]/.test(t.secret)){for(var s,r,n,a=l.querySelectorAll('iframe[data-secret="'+t.secret+'"]'),o=l.querySelectorAll('blockquote[data-secret="'+t.secret+'"]'),c=new RegExp("^https?:$","i"),i=0;i<o.length;i++)o[i].style.display="none";for(i=0;i<a.length;i++)s=a[i],e.source===s.contentWindow&&(s.removeAttribute("style"),"height"===t.message?(1e3<(r=parseInt(t.value,10))?r=1e3:~~r<200&&(r=200),s.height=r):"link"===t.message&&(r=new URL(s.getAttribute("src")),n=new URL(t.value),c.test(n.protocol))&&n.host===r.host&&l.activeElement===s&&(d.top.location.href=t.value))}},d.addEventListener("message",d.wp.receiveEmbedMessage,!1),l.addEventListener("DOMContentLoaded",function(){for(var e,t,s=l.querySelectorAll("iframe.wp-embedded-content"),r=0;r<s.length;r++)(t=(e=s[r]).getAttribute("data-secret"))||(t=Math.random().toString(36).substring(2,12),e.src+="#?secret="+t,e.setAttribute("data-secret",t)),e.contentWindow.postMessage({message:"ready",secret:t},"*")},!1)))}(window,document); //# sourceURL=https://www.aeologic.com/blog/wp-includes/js/wp-embed.min.js </script> https://www.aeologic.com/blog/wp-content/uploads/2020/06/Learning-To-Rank-in-Solr-1.png1080622With the Learning To Rank (or LTR for short) contrib module you can configure and run machine learned ranking models in Solr. The module also supports feature extraction inside Solr. The only thing you need to do outside Solr is train your own ranking model. Learning to Rank Concepts Re-Ranking Re-Ranking allows you to run a simple query for matching documents and then re-rank the top N documents using the scores from a different, more complex query. This page describes the use of LTR complex queries, information on other rank queries included in the Solr distribution can be found on the Query Re-Ranking page. Learning To Rank Models In information retrieval systems, Learning to Rank is used to re-rank the top N retrieved documents using trained machine learning models. The hope is that such sophisticated models can make more nuanced ranking decisions than standard ranking functions like TF-IDF or BM25. Ranking Model A ranking model computes the scores used to rerank documents. Irrespective of any particular algorithm or implementation, a ranking model’s computation can use three types of inputs: parameters that represent the scoring algorithm features that represent the document being scored features that represent the query for which the document is being scored Feature A feature is a value, a number, that represents some quantity or quality of the document being scored or of the query for which documents are being scored. For example documents often have a ‘recency’ quality and ‘number of past purchases’ might be a quantity that is passed to Solr as part of the search query. Normalizer Some ranking models expect features on a particular scale. A normalizer can be used to translate arbitrary feature values into normalized values e.g., on a 0..1 or 0..100 scale. Training Models Feature Engineering The LTR contrib module includes several feature classes as well as support for custom features. Each feature class’s javadocs contain an example to illustrate use of that class. The process of feature engineering itself is then entirely up to your domain expertise and creativity. Feature Class Example parameters External Feature Information field length FieldLengthFeature {"field":"title"} not (yet) supported field value FieldValueFeature {"field":"hits"} not (yet) supported original score OriginalScoreFeature {} not applicable solr query SolrFeature {"q":"{!func} recip(ms(NOW,last_modified) ,3.16e-11,1,1)"} supported solr filter query SolrFeature {"fq":["{!terms f=category}book"]} supported solr query + filter query SolrFeature {"q":"{!func} recip(ms(NOW,last_modified), 3.16e-11,1,1)", "fq":["{!terms f=category}book"]} supported value ValueFeature {"value":"${userFromMobile}","required":true} supported (custom) (custom class extending Feature) Normalizer Class Example parameters Identity IdentityNormalizer {} MinMax MinMaxNormalizer {"min":"0", "max":"50" } Standard StandardNormalizer {"avg":"42","std":"6"} (custom) (custom class extending Normalizer) Feature Extraction The ltr contrib module includes a [features transformer] to support the calculation and return of feature values for feature extraction purposes including and especially when you do not yet have an actual reranking model. Feature Selection and Model Training Feature selection and model training take place offline and outside Solr. The ltr contrib module supports two generalized forms of models as well as custom models. Each model class’s javadocs contain an example to illustrate configuration of that class. In the form of JSON files your trained model or models (e.g., different models for different customer geographies) can then be directly uploaded into Solr using provided REST APIs. General form Class Specific examples Linear LinearModel RankSVM, Pranking Multiple Additive Trees MultipleAdditiveTreesModel LambdaMART, Gradient Boosted Regression Trees (GBRT) Neural Network NeuralNetworkModel RankNet (wrapper) DefaultWrapperModel (not applicable) (custom) (custom class extending AdapterModel) (not applicable) (custom) (custom class extending LTRScoringModel) (not applicable) Quick Start with LTR The "techproducts" example included with Solr is pre-configured with the plugins required for learning-to-rank, but they are disabled by default. To enable the plugins, please specify the solr.ltr.enabled JVM System Property when running the example: Uploading Features To upload features in a /path/myFeatures.json file, please run: To view the features you just uploaded please open the following URL in a browser: Example: /path/myFeatures.json Extracting Features To extract features as part of a query, add [features] to the fl parameter, for example: The output XML will include feature values as a comma-separated list, resembling the output shown here: Uploading a Model To upload the model in a /path/myModel.json file, please run: To view the model you just uploaded please open the following URL in a browser: Example: /path/myModel.json Running a Rerank Query To rerank the results of a query, add the rq parameter to your search, for example: The addition of the rq parameter will not change the output XML of the search. To obtain the feature values computed during reranking, add [features] to the fl parameter, for example: The output XML will include feature values as a comma-separated list, resembling the output shown here: External Feature Information The ValueFeature and SolrFeature classes support the use of external feature information, efi for short. Uploading Features To upload features in a /path/myEfiFeatures.json file, please run: To view the features you just uploaded please open the following URL in a browser: Example: /path/myEfiFeatures.json As an aside, you may have noticed that the myEfiFeatures.json example uses "store":"myEfiFeatureStore" attributes: read more about feature store in the LTR Lifecycle section of this page. Extracting Features To extract myEfiFeatureStore features as part of a query, add efi.* parameters to the [features] part of the fl parameter, for example: Uploading a Model To upload the model in a /path/myEfiModel.json file, please run: To view the model you just uploaded please open the following URL in a browser: Example: /path/myEfiModel.json Running a Rerank Query To obtain the feature values computed during reranking, add [features] to the fl parameter and efi.* parameters to the rq parameter, for example: Notice the absence of efi.* parameters in the [features] part of the fl parameter. Extracting Features While Reranking To extract features for myEfiFeatureStore features while still reranking with myModel: Notice the absence of efi.* parameters in the rq parameter (because myModel does not use efi feature) and the presence of efi.* parameters in the [features] part of the fl parameter (because myEfiFeatureStore contains efi features). Read more about model evolution in the LTR Lifecycle section of this page. Training Example Example training data and a demo train_and_upload_demo_model.py script can be found in the solr/contrib/ltr/example folder in the Apache lucene-solr Git repository (mirrored on github.com). This example folder is not shipped in the Solr binary release. Installation of LTR The ltr contrib module requires the dist/solr-ltr-*.jar JARs. LTR Configuration Learning-To-Rank is a contrib module and therefore its plugins must be configured in solrconfig.xml. Minimum Requirements Include the required contrib JARs. Note that by default paths are relative to the Solr core so they may need adjustments to your configuration, or an explicit specification of the $solr.install.dir.<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-ltr-d.*.jar" /> Declaration of the ltr query parser.<queryParser name="ltr" class="org.apache.solr.ltr.search.LTRQParserPlugin"/> Configuration of the feature values cache.<cache name="QUERY_DOC_FV" class="solr.search.LRUCache" size="4096" initialSize="2048" autowarmCount="4096" regenerator="solr.search.NoOpRegenerator" /> Declaration […]