Abstract: A method of generating ontologies for a Virtual Assistant across different languages may include extracting a plurality of tokens in a first language from a plurality of web resources in a web domain that includes the Virtual Assistant. The web resources may be made available in a first language and a second language. The method may also include determining a first part-of-speech (POS) for each of the plurality of tokens, where the first POS may be specific to the first language. The method may additionally include mapping the first POS to a second POS from a standardized set of POS's that are general across the first language and the second language, and generating a plurality of lemmas from the plurality of tokens. The method may further include displaying a network representing the ontology.

Abstract: Searches for content may be improved with unique reserved phrases. Reserved phrases may direct queries to specific preselected section of content. Synonyms may be generated and associated with a reserved phrase such that even when queries do not include reserved phrases, the synonyms may be used to map queries to the reserved phrases and the associated content. Synonyms may be generated and filtered such that a synonym is only associated with one reserved phrase thereby reducing search ambiguity.

Abstract: A method of automatically generating a lemma dictionary from a web resource may include extracting a plurality of tokens from text-based documents within the web resource, and generating a plurality of N-grams from the plurality of tokens. The method may additionally include receiving one or more filter definitions that identify valid N-grams, and filtering the plurality of N-grams using the one or more filter definitions to generate a lemma dictionary. The method may further include generating an ontology that comprises the lemma dictionary.

Abstract: Embodiments of the invention provide systems and methods for processing of a text string. More specifically, embodiments of the present invention provide for contextual, fuzzy recognition of text strings such as, for example, product or company names in user queries to an automated virtual assistant or search service. The recognition can be consider contextual as it can function even when the string is embedded, e.g., in a larger sentence, and it can be considered fuzzy as it does not require a perfect match with the catalog of strings or lists of entities available. Embodiments can also define the appropriate reaction of the automated system to ambiguous matches. Embodiments couple the identification of one or more ambiguous references to entities in text queries to a topic identifier and adapt the response of the automated system depending on the occurrence of ambiguous references.

Abstract: A method of mapping ontologies between languages may include receiving a first ontology in a first language, where the first ontology includes a first plurality of lemmas and a plurality of relationships between the plurality of lemmas. The method may also include receiving a second plurality of lemmas in a second language, and mapping each of the second plurality of lemmas in the second language to a respective lemma in the first plurality of lemmas in the first language. The method may additionally include generating a second ontology in the second language by using the plurality of relationships in the first ontology to create relationships between the second plurality of lemmas in the second language.

Abstract: Searches for content may be improved with unique reserved phrases. Reserved phrases may direct queries to specific preselected section of content. Synonyms may be generated and associated with a reserved phrase such that even when queries do not include reserved phrases, the synonyms may be used to map queries to the reserved phrases and the associated content. Synonyms may be generated and filtered such that a synonym is only associated with one reserved phrase thereby reducing search ambiguity.

Abstract: A method of mapping ontologies between languages may include receiving a first ontology in a first language, where the first ontology includes a first plurality of lemmas and a plurality of relationships between the plurality of lemmas. The method may also include receiving a second plurality of lemmas in a second language, and mapping each of the second plurality of lemmas in the second language to a respective lemma in the first plurality of lemmas in the first language. The method may additionally include generating a second ontology in the second language by using the plurality of relationships in the first ontology to create relationships between the second plurality of lemmas in the second language.

Abstract: A method of generating ontologies for a Virtual Assistant across different languages may include extracting a plurality of tokens in a first language from a plurality of web resources in a web domain that includes the Virtual Assistant. The web resources may be made available in a first language and a second language. The method may also include determining a first part-of-speech (POS) for each of the plurality of tokens, where the first POS may be specific to the first language. The method may additionally include mapping the first POS to a second POS from a standardized set of POS's that are general across the first language and the second language, and generating a plurality of lemmas from the plurality of tokens. The method may further include displaying a network representing the ontology.

Abstract: A method of automatically generating a lemma dictionary from a web resource may include extracting a plurality of tokens from text-based documents within the web resource, and generating a plurality of N-grams from the plurality of tokens. The method may additionally include receiving one or more filter definitions that identify valid N-grams, and filtering the plurality of N-grams using the one or more filter definitions to generate a lemma dictionary. The method may further include generating an ontology that comprises the lemma dictionary.