Hi Roopa, that's clearer now, thanks. I don't think there's any support for feature extraction from children when calculating the feature vector of a parent. It's an interesting feature though. I would love to design and implement such functionality. If you want to do that on your own I recommend working from the current supported features implementations (/solr/contrib/ltr/src/java/org/apache/solr/ltr/feature)
Cheers -------------------------- Alessandro Benedetti Apache Lucene/Solr Committer Director, R&D Software Engineer, Search Consultant www.sease.io On Tue, 22 Jun 2021 at 19:47, Roopa Rao <roop...@gmail.com> wrote: > Hi Alessandro, > > Thanks for the response. > > I am using version Solr 6.6 > > Basically, I have parent documents and multiple child documents for each > parent. > I am trying to create features and get feature scores on parent attributes > (which is straightforward) and child attributes (which is what I am looking > for examples). > And then rerank documents based on an LTR model which will use these > features (on both parent & child). > > Enclosing the parent-child structure and the query construction (where you > can see I am using a child transformer) and also a sample feature, current > sample features score output. > > > <doc> > <str name="id">abc-1</str> > <str name="unique_id_s">feature-1281835650</str> > <str name="type">parent-docs</str> > <str name="title_s">Parent title1 text1 </str> > <str name="summary_s">Parent summary1 text2</str> > > <doc> > <str name="id">child-doc-12345</str> > <str name="unique_id_s">feature-1281835650</str> > <str name="type">child-docs</str> > <str name="child_doc_resource_id_s">9735</str> > <str name="child_doc_resource_desc_s">A sample child doc desc</str> > <date name="child_doc_dt">2021-09-01T00:00:00Z</date> > <arr name="child_doc_product_s_mult"> > <str>productA</str> > <str>productB</str> > <str>productC</str> > </arr> > </doc> > <doc> > <str name="id">child-doc-56788</str> > <str name="unique_id_s">feature-1281835650</str> > <str name="type">child-docs</str> > <str name="child_doc_resource_id_s">3426</str> > <str name="child_doc_resource_desc_s">A sample child doc desc - > 2</str> > <date name="child_doc_dt">2021-09-02T00:00:00Z</date> > <arr name="child_doc_product_s_mult"> > <str>productD</str> > <str>productE</str> > <str>productF</str> > </arr> > </doc> > </doc> > > Query construction: > Get documents based on search of parent document attributes - title, > summary. > Get the corresponding child document in the response, filtered by products > eligible to, restrict to 1 (for display purposes). > Rerank based on a model and get feature scores on both attributes on parent > and attributes on child. > > https://localhost:8983/testhandler?q=trying to > > test&rows=100&start=0&q.op=AND&timeAllowed=20000&fl=id,score,title_s,summary_s,[features > store=testFeatureStore],[explain]&fl=_childDocuments_&fl=[child > parentFilter='type:parent-docs' childFilter='((type:(child-docs)) AND > ({!terms f=child_doc_product_s_mult}productA,productD))' > limit=1]&sort=score > > desc&fq=(type:(parent-docs))&defType=edismax&df=title_qf_default&q.alt=*:*&pf=title_qf_default^2.0 > title_qf_synonym^2.0&qf=title_qf_default^2.0 > summary_qf_default^1.0&sow=false&lowercaseOperators=false&tie=0.0&rq={!ltr > model=testModel reRankDocs=100 efi.uq=$q} > > Here trying to create features for title_s match with uq (user query) - > which works fine since it is on the parent. > Sample feature: > { > "name": "feature_title_match", > "class": "org.apache.solr.ltr.feature.SolrFeature", > "params": { > "q": "{!dismax qf=title_qf_default}${uq:none}" > }, > "store": "testFeatureStore" > } > > Similarly I need to create features for child_doc_resource_desc_s match > with uq (user query) and a few more features on child_doc attributes. > > Right now I am getting scores on the parent attributes as expected. > > *However writing features on the child document attributes and getting > feature scores for them is what I am looking for:* > Current Sample output: > > <str > > name="[features]">originalScore=61.886406,feature_title_match=8.004536,feature_summary_match=3.340,feature_title_synonym_expansion=15.471601</str> > > Similarly want to build features: feature_child_doc_resource_desc which > would give a feature score of user query matched with > child_doc_resource_desc_s attribute of the child doc: > > So an output like this may be? or feature scores on child comes under each > child document not sure > <str > > name="[features]">originalScore=61.886406,feature_title_match=8.004536,feature_summary_match=3.340,feature_title_synonym_expansion=15.471601,feature_child_doc_resource_desc=value1</str> > > > Thank you! > Roopa > > On Tue, Jun 22, 2021 at 1:04 PM Alessandro Benedetti <a.benede...@sease.io > > > wrote: > > > Hi Roopa, > > can you elaborate a bit better? > > Child documents are documents nonetheless, so you can query them, rank > them > > and re0rank them. > > So, what are you trying to do? > > Are you using any block join related query parsers? > > Do you want to combine it with learning to rank? > > How? > > Let us know and we can try to help! > > > > -------------------------- > > Alessandro Benedetti > > Apache Lucene/Solr Committer > > Director, R&D Software Engineer, Search Consultant > > > > www.sease.io > > > > > > On Mon, 21 Jun 2021 at 19:12, Roopa Rao <roop...@gmail.com> wrote: > > > > > Hi, > > > > > > Is there a way to get the feature score on fields on the childDocuments > > in > > > LTR. > > > Note that there could be multiple childDocuments. > > > > > > If there are example features that can be provided which uses query on > > the > > > child documents will be helpful > > > > > > Thank you, > > > Roopa > > > > > >
