在任务型的对话系统中,对话状态跟踪(DST)的目标是从对话历史中监控对话的状态。
DST的输入:Intent+Slot+History;输出:State或State Vector
DST中的State用一组Slot-Value键值对表示;
一、基于规则的DST
二、基于模型的DST
At a high level, given a dialog context and a candidate slot- value pair, our model outputs a score indicating the relevance of the candidate.
In other words, the approach is similar to a sentence pair classification task.
- The first input corresponds to the dialog context, and it consists of the system utterance from the previous turn and the user utterance from the cur- rent turn. The two utterances are separated by a [SEP] token.
- The second input is the candidate slot-value pair. We simply represent the candidate pair as a sequence of tokens (words or pieces of words).
At each turn, the proposed BERT-based model is used to estimate the probability score of every candidate slot-value pair.After that, only pairs with predicted probability equal to at least 0.5 are chosen as the final prediction for the turn.