Flexible and Scalable State Tracking Framework for Goal-Oriented
Dialogue Systems
release_3sixlvuivnen7ihuapt6mlepqi
by
Rahul Goel, Shachi Paul, Tagyoung Chung, Jeremie Lecomte, Arindam
Mandal, Dilek Hakkani-Tur
2018
Abstract
Goal-oriented dialogue systems typically rely on components specifically
developed for a single task or domain. This limits such systems in two
different ways: If there is an update in the task domain, the dialogue system
usually needs to be updated or completely re-trained. It is also harder to
extend such dialogue systems to different and multiple domains. The dialogue
state tracker in conventional dialogue systems is one such component - it is
usually designed to fit a well-defined application domain. For example, it is
common for a state variable to be a categorical distribution over a
manually-predefined set of entities (Henderson et al., 2013), resulting in an
inflexible and hard-to-extend dialogue system. In this paper, we propose a new
approach for dialogue state tracking that can generalize well over multiple
domains without incorporating any domain-specific knowledge. Under this
framework, discrete dialogue state variables are learned independently and the
information of a predefined set of possible values for dialogue state variables
is not required. Furthermore, it enables adding arbitrary dialogue context as
features and allows for multiple values to be associated with a single state
variable. These characteristics make it much easier to expand the dialogue
state space. We evaluate our framework using the widely used dialogue state
tracking challenge data set (DSTC2) and show that our framework yields
competitive results with other state-of-the-art results despite incorporating
little domain knowledge. We also show that this framework can benefit from
widely available external resources such as pre-trained word embeddings.
In text/plain
format
Archived Files and Locations
application/pdf 262.4 kB
file_drqkl3hfdjfsbgduqh5nlpr4li
|
arxiv.org (repository) web.archive.org (webarchive) |
1811.12891v1
access all versions, variants, and formats of this works (eg, pre-prints)