feature: lookup intent parser #121
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
mattgathu
requested review from
adrienball,
ClemDoum and
klefevre
and removed request for
adrienball and
ClemDoum
adrienball
requested changes
Feb 28, 2019
A new hashmap based intent parser. The normalized/canonical form of an utterance serves as the key and the value is tuple of `(intent_id, [vec_of_slots_ids])` Once a lookup is done at inference, the intent and slots are retrieved by matching their ids to a vec of intent names and a vec of slot names respectively. This is the rust implementation of snipsco/snips-nlu#759
* refactor text preprocessing and avoid key generation * refactor replace entities and avoid range calculations
the first hashmap lookup is based on a key generated on the processed text (text with entity replacements). If this lookup returns no value a second lookup using the plain text is done, this lookup corresponds to having no entity replacements.
mattgathu
force-pushed
the
feature/lookup_intent_parser
branch
from
5a81b94
to
ae55fac
Compare
adrienball
requested changes
Mar 1, 2019
There was a problem hiding this comment.
On top of the comments, you must also update the logic in intent_parser/mod.rs and add the support of the new intent parser.
This is tested through the loading of data/tests/models/nlu_engine and data/tests/models/nlu_engine.zip, hence we should re-generate these files using the new lookup intent parser.
register lookup intent parser in the nlu engine metadata enum
mattgathu
force-pushed
the
feature/lookup_intent_parser
branch
from
e0f383e
to
54755db
Compare
* rebuilt the test nlu_engine dataset
Refactor lookup hashmap to use hashes as keys instead of actual string patterns. The reduces the size of the model.
…_hashing Add Lookup Intent Parser key hashing
adrienball
force-pushed
the
feature/lookup_intent_parser
branch
from
5549133
to
526bc37
Compare
adrienball
approved these changes
Jul 11, 2019
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
A new hashmap based intent parser.
The normalized/canonical form of an utterance serves as the key and the value is tuple of
(intent_id, [vec_of_slots_ids])Once a lookup is done at inference, the intent and slots are retrieved by matching their ids to a vec of intent names and a vec of slot names respectively.
This is the rust implementation of snipsco/snips-nlu#759