Snips Nlu Versions Save

Added

• Add intents filter parameter in parsing CLI #858
• Add documentation about intents filters #858
• Update dependencies for better python3.8 support #867

Added

• Allow to bypass the model version check #830
• Persist CustomEntityParser license when needed #832
• Document metrics CLI #839
• Allow to fit SnipsNLUEngine with a Dataset object #840

Changed

• Update snips-nlu-parsers dependency upper bound to 0.5 #850

Fixed

• Invalidate importlib caches after dynamically installing module #838
• Automatically generate documentation for supported languages and builtin entities #841
• Fix issue when cleaning up crfsuite files #843
• Fix filemode of persisted crfsuite files #844

Added

• Add new intent parser: LookupIntentParser #759

Changed

• Replace DeterministicIntentParser by LookupIntentParser in default configs #829
• Bumped snips-nlu-parsers to 0.3.x introducing new builtin entities:
  • snips/time
  • snips/timePeriod
  • snips/date
  • snips/datePeriod
  • snips/city
  • snips/country
  • snips/region

Added

• Add filter for entity match feature #814
• Add noise re-weight factor in LogRegIntentClassifier #815
• Add warning logs and improve errors #821
• Add random seed parameter in training CLI #819

Fixed

• Fix non-deterministic behavior #817
• Import modules lazily to speed up CLI startup time #819
• Removed dependency on semantic_version to accept "subpatches" number #825

Fixed

• Fix non-deterministic behavior #817

Changed

• Re-score ambiguous DeterministicIntentParser results based on slots #791
• Accept ambiguous results from DeterministicIntentParser when confidence score is above 0.5 #797
• Avoid generating number variations when not needed #799
• Moved the NLU random state from the config to the shared resources #801
• Reduce custom entity parser footprint in training time #804
• Bumped scikit-learn to >=0.21,<0.22 for python>=3.5 and >=0.20<0.21 for python<3.5 #801
• Update dependencies #811

Fixed

• Fixed a couple of bugs in the data augmentation which were making the NLU training non-deterministic #801
• Remove deprecated code in dataset generation #803
• Fix possible override of entity values when generating variations #808

Fixed

• Raise an error when using unknown intents in intents filter #788
• Fix issue with stop words in DeterministicIntentParser #789

Added

• Advanced inference logging in the CRFSlotFiller #776
• Improved failed linking error message after download of resources #774
• Improve handling of ambiguous utterances in DeterministicIntentParser #773

Changed

• Remove normalization of confidence scores in intent classification #782

Fixed

• Fixed a crash due to missing resources when refitting the CRFSlotFiller #771
• Fixed issue with egg fragments in download cli #769
• Fixed an issue causing the None intent to be ignored when using the parse API in conjunction with intents and top_n #781

Added

• Support for Portuguese: "pt_pt" and "pt_br"

Changed

• Enhancement: leverage entity scopes of each intent in deterministic intent parser

Fixed

• Issue with intent classification reducing classification accuracy
• Issue resulting in a mutation of the CRFSlotFillerConfig
• Wrong required resources of the DeterministicIntentParser
• Issue with non ASCII characters when using the parsing CLI with Python2