Learning dialogue state tracking with limited labeled data
Assigneesalesforce.com, inc.
InventorsChien-Sheng Wu, Chu Hong Hoi, Caiming Xiong
Life of this patent
Estimating the term…
Abstract
Embodiments described in this disclosure illustrate the use of self-/semi supervised approaches for label-efficient DST in task-oriented dialogue systems. Conversational behavior is modeled by next response generation and turn utterance generation tasks. Prediction consistency is strengthened by augmenting data with stochastic word dropout and label guessing. Experimental results show that by exploiting self-supervision the joint goal accuracy can be boosted with limited labeled data.
Claims20
A method for self-supervised training of a dialogue state tracking (DST) module, the method comprising:
- receiving, from a database, a first input of unlabeled dialogue data including a time sequence of dialogue pairs, each dialogue pair including a respective unlabeled user utterance and a respective unlabeled system response;
- generating, via the DST module, a predicted system response subsequent to a first dialogue pair based on a first set of dialogue pairs that occur by and include the first dialogue pair in the time sequence of dialogue pairs and a predicted dialogue state from the first dialogue pair;
- generating, via the DST module, a predicted user utterance corresponding to the first dialogue pair based on a second set of dialogue pairs that occur prior to the first dialogue pair in the time sequence of dialogue pairs and the predicted dialogue state from the first dialogue pair;
- computing an unsupervised loss metric based on the predicted system response and the generated user utterance for the first dialogue pair;
- and
- updating the DST module based on the unsupervised loss metric.
A system for self-supervised training of a dialogue state tracking (DST) module, the method comprising:
- a memory storing instructions for self-supervised training of the DST module;
- and
- a processor configured to read and execute the instructions from the memory to:
- receive, from a database, a first input of unlabeled dialogue data including a time sequence of dialogue pairs, each dialogue pair including a respective unlabeled user utterance and a respective unlabeled system response;
- generate, via the DST module, a predicted system response subsequent to a first dialogue pair based on a first set of dialogue pairs that occur by and include the first dialogue pair in the time sequence of dialogue pairs and a predicted dialogue state from the first dialogue pair;
- generate, via the DST module, a predicted user utterance corresponding to the first dialogue pair based on a second set of dialogue pairs that occur prior to the first dialogue pair in the time sequence of dialogue pairs and the predicted dialogue state from the first dialogue pair;
- compute an unsupervised loss metric based on the predicted system response and the generated user utterance for the first dialogue pair;
- and
- update the DST module based on the unsupervised loss metric.
A non-transitory processor-readable storage medium storing processor-executable instructions for self-supervised training of a dialogue state tracking (DST) module, the instructions being executed by a processor to:
- receive, from a database, a first input of unlabeled dialogue data including a time sequence of dialogue pairs, each dialogue pair including a respective unlabeled user utterance and a respective unlabeled system response;
- generate, via the DST module, a predicted system response subsequent to a first dialogue pair based on a first set of dialogue pairs that occur by and include the first dialogue pair in the time sequence of dialogue pairs and a predicted dialogue state from the first dialogue pair;
- generate, via the DST module, a predicted user utterance corresponding to the first dialogue pair based on a second set of dialogue pairs that occur prior to the first dialogue pair in the time sequence of dialogue pairs and the predicted dialogue state from the first dialogue pair;
- compute an unsupervised loss metric based on the predicted system response and the generated user utterance for the first dialogue pair;
- and
- update the DST module based on the unsupervised loss metric.
Dependencies are inferred from the claim text.