# Dialog State Tracking: A Neural Reading Comprehension Approach

### Overview

• Estimate the current belief state of a dialog given all the preceding conversation.
• The dialog state at each turn is defined as a distribution over a set of predefined variables.
• Most DST problems assume a fixed ontology.
• Key Contributions of Paper -
• Formulate DST as a Reading Comprehension problem.
• 3 decisions
• slot carryover
• slot type decision by a slot
• slot span decision using attentive

### Architecture

Dialog

A sub-dialog $$D_t$$ of a dialog D is defined by the values of the constituent slots $$S_t$$ and hence Dt is defined as $$D_t = {s_1(t), s_2(t),....,s_M(t)}$$.

Encoding

• Concatenate the user utterances and agent utterances. $${u_1, a_1, u_2, a_2... ,u_t}$$
• To differentiate, add [U] before user utterance and [A] before agent utterance.
• Use BERT to form pi for each token in the dialog sequence and pass them as input to an RNN - $${d_1, d_2, d_L} = RNN(p1, p2, ..., p_L)$$.
• Dialog embedding at turn t is et $$e_t = (d_1;d_L)$$
• To encode question, we ask what is the value of slot i for each of the M slots. Hence M questions.

Models

1. Slot Carryover Model - A model to decide if we’ve to carry over the slot value from previous turn or not. This is equal to $$sigmoid(e(t). W_i)$$ . Wi is for all slots - the carry over model for all slots is predicted together.
2. Slot Type Model - For every slot, predict if it belongs to {Yes, No, DontCare, Span}. We concatenate the dialog representation with the question embedding and pass it through a feed forward layer followed by a softmax.
3. Slot Span Model - The question vector qi acts as the question and the dialog encoding $${d_1, d_2, d_L}$$ acts as the context. Pick a span within the context that has the slot.

Setup

1. For slot carry over models, we do a joint prediction and get M binary vector (whether to carry over the value for all slots).
2. For slot type and slot span models, we treat dialog question pairs (Dt, qi) as separate prediction tasks for each slot.

### Results

Paper Accuracy on MultiWoz 2.0
This paper 39.21
HyST (ensemble) 44.22
This paper + JST 47.33