@@ -407,7 +407,7 @@ Some cross-domain feature extraction methods have been proposed \cite{RefWorks:
\subsubsection{ConceptNet and WordNet}
Semantic information can be obtained from \textit{ConceptNet}\cite{RefWorks:doc:5e382bf3e4b0034ec2324aed}, which is a graph connecting words and phrases with labelled and weighted edges expressing semantic relations between the words. As our goal is to obtain features of a product, the relations we are most interested in are:
Semantic information can be obtained from \textit{ConceptNet}\cite{RefWorks:doc:5e382bf3e4b0034ec2324aed}, which is a common-sense knowledge graph connecting words and phrases with labelled and weighted edges expressing semantic relations between the words. As our goal is to obtain features of a product, the relations we are most interested in are:
\begin{itemize}
\item\textit{CapableOf} for capabilities of products;
We evaluate our ontology extraction method using human annotators both independently and against ontologies extracted using ConceptNet and WordNet. We evaluate the ontologies extracted for a variety of five randomly selected products which were not included in the training data for the classifier: \textit{watches}, \textit{televisions}, . The full ontologies extracted for these products are included in Appendix \ref{sec:ontology_appendix}.
In this section, we evaluate our ontology extraction method using human annotators both independently and against ontologies extracted using ConceptNet and WordNet. Furthermore, we independently evaluate the generalisation of the masked BERT method by experimenting with the number of the product categories used for its training.
\subsection{Ontology evaluation}
Furthermore, we independently evaluate the generalisation of the masked BERT method by experimenting with the number of the product categories used for its training.
We evaluate five ontologies extracted for a variety of randomly selected products which were not included in the training data for the classifier: \textit{watches}, \textit{televisions}, \textit{necklaces}, \textit{stand mixers}, and \textit{video games}. For each product, we use 100,000 review texts as input to the ontology extractor, except for \textit{stand mixer}, for which we could only obtain 28,768 review texts. The full ontologies extracted for each of the products are included in Appendix \ref{sec:ontology_appendix}.
\subsection{Ontology evaluation}
We also extractontologies for the five products from ConceptNet and WordNet for comparison. For ConceptNet, we observe