Automatic discovery of business-specific terminology
An IVR and chatbot, or other system, employing a language model, the language model resulting from a method and computer product encoding the method is available for preparing a domain or subdomain specific glossary. The method included using probabilities, word context, common terminology and different terminology to identify domain and subdomain specific language and a related glossary updated according to the method.
1. An interactive response system comprising:
a processor; and
a memory communicatively coupled to the processor comprising executable instructions that, when executed by the processor, cause the system to perform acts comprising:
identify terminology that is the same for all subdomains in a domain to define a common terminology;
subtract the common terminology from a language model to identify subdomain-specific terminology for each subdomain;
calculate a priori appearance probability of a series of words using the subdomain terminology for each subdomain; and
automatically determine similarity of meanings of terms across subdomains by identifying terms with the similar appearance probability within a series of words.
2. The interactive response system of claim 1 , wherein terms with a high appearance probability are deemed specific to a subdomain.
3. The interactive response system of claim 1 , the acts further comprising determine that subdomain-specific terminology having the same appearance probability and appearing in the same context have equivalent meaning.
4. The interactive response system of claim 1 , the acts further compare further comprising comparing the appearance probability for each series of words to determine terms important to each subdomain.
5. The interactive response system of claim 1 , wherein the a priori appearance probability is calculated using a word lattice.
6. The interactive response system of claim 1 , wherein the a priori appearance probability is calculated using word embedding.
7. The interactive response system of claim 1 , wherein the subdomain is a specific business within an industry and the domain is the industry.
8. The interactive response system of claim 1 , wherein the subdomain is business units common in an industry and the domain is the industry.
9. The interactive response system of claim 1 , the acts further comprising extract subdomain-specific technology.
10. The interactive response system of claim 1 , the acts further comprising populate subdomain-specific glossaries with the subdomain-specific terminology.
11. The interactive response system of claim 1 , further comprising a chatbot.
12. The interactive response system of claim 1 , further comprising an interactive voice response system.
13. A method comprising:
identifying terminology that is the same for all subdomains in a domain to define a common terminology;
subtracting the common terminology from a language model to identify subdomain-specific terminology for each subdomain;
calculating a priori appearance probability of a series of words using the subdomain terminology for each subdomain; and
automatically determining similarity of meanings of terms across subdomains by identifying terms with the similar appearance probability within a series of words.
14. The method of claim 13 , wherein terms with a high appearance probability are deemed specific to a subdomain.
15. The method of claim 13 , the method further comprising determining that subdomain-specific terminology having the same appearance probability and appearing in the same context have equivalent meaning.
16. The method of claim 13 , the method further comprising comparing the appearance probability for each series of words to determine terms important to each subdomain.
17. The method of claim 13 , wherein the a priori appearance probably is calculated using a word lattice.
18. The method of claim 13 , wherein the a priori appearance probability is calculated using word embedding.
19. The method of claim 13 , wherein the subdomain is a specific business within an industry and the domain is the industry.
20. The method of claim 13 , wherein the subdomain is business units common in an industry and the domain is the industry.
21. The method of claim 13 , the method further comprising extracting subdomain-specific technology.
22. The method of claim 13 , the method further comprising populating subdomain-specific glossaries with the subdomain-specific terminology.