Neural Belief Tracker: Data-Driven Dialogue State Tracking

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.

Scalable Neural Dialogue State Tracking

“…• we provide empirical evidences (three languages of the WOZ2.0 dataset [7]) that the proposed G-SAT model considerably reduces the latency time with respect to state-of-art DST systems (i.e. over 15 times faster), while keeping the dialogue state prediction inline with such systems;…”

“…Following this research line, [5] proposed a word-based DST (based on a delexicalisation approach) that jointly models SLU and DST, and directly maps from the utterances to an updated belief state. [7] proposed a data-driven approach for DST, named neural belied tracker (NBT), which learns a vector representation for each slot-value pair and compares them with the vector representation of the user utterance to predict if the user has expressed the corresponding slot-value pair. The NBT model uses pre-trained semantic embeddings to train a model without semantic lexicon.…”

“…We compared our G-SAT model against seven DST models. The Delexicalisation model [7] uses a delexicalisation approach (i.e. replacing slot value tokens with generic terms) and requires large semantic dictionaries, while all the other approaches are data driven.…”

“…Joint Goal Turn Request Delexicalisation Model [7] 70.8 87.1 NBT -CNN [7] 84.2 91.6 NBT -DNN [7] 84.4 91.2 CNN [16] 86.9 95.4 GLAD [9] 88.1 97.1 GCE [10] 88.5 97.4 StateNet PSI [8] 88.9 -Our Approach (G-SAT) 88.7 96.9 Table 1. Dialog state tracking results on the WOZ2.0 English testset.…”

Proceedings of ACL 2017, Tutorial Abstracts

“…More recent work on Neural Dialog Managers that provide conjoint representations between the utterances, slot-value pairs as well as knowledge graph representations Mrkšić et al, 2016) demonstrate that using neural dialog models can overcome current obstacles of deploying dialogue systems in larger dialog domains.…”