convlab2.policy.rule.crosswoz package

Submodules

convlab2.policy.rule.crosswoz.evaluate module

convlab2.policy.rule.crosswoz.evaluate.begin_active_tuple_num(data)
convlab2.policy.rule.crosswoz.evaluate.begin_da_type(data)
convlab2.policy.rule.crosswoz.evaluate.calculateF1(predict_golden)
convlab2.policy.rule.crosswoz.evaluate.calculateJointState(predict_golden)
convlab2.policy.rule.crosswoz.evaluate.calculateSlotState(predict_golden)
convlab2.policy.rule.crosswoz.evaluate.end_usr_da_type(data)
convlab2.policy.rule.crosswoz.evaluate.eval_begin_da_predict(data)
convlab2.policy.rule.crosswoz.evaluate.eval_simulator_performance(data, goal_type=None)
convlab2.policy.rule.crosswoz.evaluate.eval_state_predict(data)
convlab2.policy.rule.crosswoz.evaluate.read_zipped_json(filepath, filename)

convlab2.policy.rule.crosswoz.rule_simulator module

class convlab2.policy.rule.crosswoz.rule_simulator.Simulator

Bases: convlab2.policy.policy.Policy

begin_da()
get_goal()
get_reward()
infer_goal_type(goal)
init_session(goal=None, state=None, turn_num=0, da_seq=[])

Init the class variables for a new session.

is_terminated()
predict(sys_act)

Predict the next agent action given dialog state.

Args:
state (dict or list of list):

when the policy takes dialogue state as input, the type is dict. else when the policy takes dialogue act as input, the type is list of list.

Returns:
action (list of list or str):

when the policy outputs dialogue act, the type is list of list. else when the policy outputs utterance directly, the type is str.

state_predict()
state_update(prev_user_da, prev_sys_da)

Module contents