Neural Belief Tracker: Data-Driven Dialogue State Tracking

TL;DR

The paper introduces Neural Belief Tracking, a data-driven approach that leverages pre-trained word vectors to improve dialogue state tracking without extensive annotated data or hand-crafted lexicons.

Contribution

It presents a novel neural framework that uses representation learning to enhance dialogue state tracking, reducing reliance on large annotated datasets and semantic lexicons.

Findings

Outperforms previous models without hand-crafted lexicons

Matches state-of-the-art performance with lexicons

Generalizes well across datasets

Abstract

One of the core components of modern spoken dialogue systems is the belief tracker, which estimates the user's goal at every step of the dialogue. However, most current approaches have difficulty scaling to larger, more complex dialogue domains. This is due to their dependency on either: a) Spoken Language Understanding models that require large amounts of annotated training data; or b) hand-crafted lexicons for capturing some of the linguistic variation in users' language. We propose a novel Neural Belief Tracking (NBT) framework which overcomes these problems by building on recent advances in representation learning. NBT models reason over pre-trained word vectors, learning to compose them into distributed representations of user utterances and dialogue context. Our evaluation on two datasets shows that this approach surpasses past limitations, matching the performance of state-of-the-art models which rely on hand-crafted semantic lexicons and outperforming them when such lexicons are not provided.