convlab2.dst.rule.multiwoz package¶
Submodules¶
convlab2.dst.rule.multiwoz.dst module¶
-
class
convlab2.dst.rule.multiwoz.dst.
RuleDST
¶ Bases:
convlab2.dst.dst.DST
Rule based DST which trivially updates new values from NLU result to states.
- Attributes:
- state(dict):
Dialog state. Function
convlab2.util.multiwoz.state.default_state
returns a default state.- value_dict(dict):
It helps check whether
user_act
has correct content.
-
init_session
()¶ Initialize
self.state
with a default state, whichconvlab2.util.multiwoz.state.default_state
returns.
-
update
(user_act=None)¶ update belief_state, request_state :param user_act: :return:
convlab2.dst.rule.multiwoz.dst_util module¶
-
convlab2.dst.rule.multiwoz.dst_util.
minDistance
(word1, word2)¶ The minimum edit distance between word 1 and 2.
-
convlab2.dst.rule.multiwoz.dst_util.
normalize_value
(value_set, domain, slot, value)¶ Normalized the value produced by NLU module to map it to the ontology value space.
- Args:
- value_set (dict):
The value set of task ontology.
- domain (str):
The domain of the slot-value pairs.
- slot (str):
The slot of the value.
- value (str):
The raw value detected by NLU module.
- Returns:
value (str): The normalized value, which fits with the domain ontology.
-
convlab2.dst.rule.multiwoz.dst_util.
special_match
(domain, slot, value)¶ special slot fuzzy matching
-
convlab2.dst.rule.multiwoz.dst_util.
str_similar
(a, b)¶