Teneo Input Processors
Bulgarian configuration properties
Per the development of the new Bulgarian Lexical Resource, the properties files of the input processing chain for Bulgarian related to abbreviations (Standard Splitting IP), auto-correction (Standard Auto Correct IP), keyboard configuration (Standard Similarity Match Correction IP) and list of consonants (System Annotations) have been reviewed to ensure correct behavior and adjustments have been performed to the Basic Number Recognizer to allow for both
, (comma) and
. (dot) as decimal markers.
Teneo NLU Ontology and Semantic Networks
Bulgarian Lexical Resource
A completely new Teneo Lexical Resource has been built for Bulgarian; the Teneo Lexical Resources are Artificial Solutions' proprietary resources containing off-the-shelf building blocks (Language Objects and Entities) to be used for the modelling of NLI solutions in Teneo Studio. Lexical Resources are a simple tick away in Teneo Studio and they give access to thousands of Language Objects and Entities ready to use as condition building blocks.
The Bulgarian Lexical Resource's Language Objects cover the most frequent Bulgarian words across all the part-of-speech categories. All the declinations and conjugation word forms are available for inflectable words (nouns, adjectives, pronouns, numerals, verbs, adverbs) as well as formal and informal language register variants for many words.
The Bulgarian Teneo Lexical Resource contains about 8.000 Language Objects, including over 300 Synonym Language Objects. It also contains Entities for country, city, color, months, weekdays, zodiac signs, numbers and ordinals.
German Lexical Resource
The word "künden" is added as a synonym for "kündigen".
Deprecated Language Objects
As of Teneo 6.1.1, annotations are correctly highlighted as such when used as entry values in Entities. Thanks to this, the NER annotations can now be used directly as entry values in the corresponding Entities. This makes the
NER_.ANNOT Language Objects in English, Italian, French, Spanish, German and Swedish superfluous and they have thus been deprecated.
Teneo Conversational Modules
Bulgarian Dialogue Resource
The Teneo 6.2 release includes a brand new Teneo Dialogue Resource for Bulgarian which contains both Syntax Flows, Class Flows and Hybrid Flows.
The Syntax Flows use linguistic rules based on the Teneo Linguistic Modelling Language exclusively and are particularly useful for identifying specific input types with high precision, for example when the end-user says "Hello", "Goodbye", etc., while the Class Flows use Teneo's native machine learning capabilities that learn how to predict intents based on the provided training data. Lastly, the Hybrid Flows use a combination of Class Match Requirements and Condition Match Requirements (linguistic syntax rules) to leverage the best aspects of both machine-learning and linguistic rules; these Flows allow for the precision of the linguistic rules and the flexibility of machine learning.
As with all Teneo Dialogue Resources, the Bulgarian Dialogue Resource is nearly production ready, but some project-time should be dedicated to adapting the Flows manually according to the needs of the project. The necessary adaptations may included ensuring that the Dialogue Resource's Triggers and/or Classes are compatible with the Project's Triggers and Classes. Projects can re-arrange and re-name the folders and change the structure if needed.
Templates for LUIS^Teneo
The Classes and their training data examples from the Dutch, English, French, German, Italian, Portuguese, Spanish and Turkish Dialogue Resources are made available in a JSON format supported by LUIS. The JSON files can be imported as new apps into LUIS and be used in conjunction with the corresponding Teneo Dialogue Resource solution when working with the LUIS^Teneo approach.
To provide better support to LUIS^Teneo, some minor adaptations of the training data of some Classes are done in the Dutch, English, French, German, Italian, Portuguese, Spanish and Turkish Dialogue Resources.
Scripted Context Multi-word input
A new scripted context
Multi-Word input has been added to all Teneo Dialogue Resources. When this context is assigned to a Trigger or Transition, user inputs consisting of only one word are prevented from triggering.