I am extracting topics from text using a predefined ontology containing 2690 concepts, wordnet(to expand concept terms with their synsets, and other morphological forms of the same word) and lucene to index ontology concepts. However, as it is very difficult to find the ground truth about the topics in the documents, it is becoming very difficult to evaluate the model. As manually tagging the correct labels will take a huge amount of time.

Are there any standard ways by which people evaluate models of topic extraction/ entity extraction, when ground truth about the topics is not clear?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.