Volkova, Svitlana and Choudhury, Pallavi and Quirk, Chris and Dolan, Bill and Zettlemoyer, Luke
Article Structure
Abstract
Procedural dialog systems can help users achieve a wide range of goals.
Introduction
Procedural dialog systems aim to assist users with a wide range of goals.
Overview of Approach
Our task-oriented dialog system understands user utterances by mapping them to nodes in dialog trees generated from instructional text.
Building Dialog Trees from Instructions
Our first problem is to convert sets of instructions for user goals to dialog trees, as shown in Figure 2.
Understanding Initial Queries
This section presents a model for classifying initial user queries to nodes in a dialog tree, which allows for a variety of different types of queries.
Understanding Query Refinements
We also developed a classifier model for mapping followup queries to the nodes in a dialog network, while maintaining a dialog state that summarizes the history of the current interaction.
The Complete Dialog System
Following the overall setup described in Section 2, we integrate the learned models into a complete dialog system.
Related work
To the best of our knowledge, this paper presents the first effort to induce full procedural dialog systems from instructional text and query click logs.
Conclusions and Future Work
This paper presented a novel approach for automatically constructing procedural dialog systems with light supervision, given only textual resources such as instructional text and search query click logs.
Topics
log-linear
Appears in 3 sentences as: log-linear (3)
In Lightly Supervised Learning of Procedural Dialog Systems
- Given a single instruction 2' with category au, we use a log-linear model to represent the distri-
Page 3, “Building Dialog Trees from Instructions”
- We employ a log-linear model and try to maximize initial dialog state distribution over the space of all nodes in a dialog network:
Page 5, “Understanding Initial Queries”
- Dialog State Update Model We use a log-linear model to maximize a dialog state distribution over the space of all nodes in a dialog network:
Page 7, “Understanding Query Refinements”
See all papers in Proc. ACL 2013 that mention log-linear.
See all papers in Proc. ACL that mention log-linear.
Back to top.
log-linear model
Appears in 3 sentences as: log-linear model (3)
In Lightly Supervised Learning of Procedural Dialog Systems
- Given a single instruction 2' with category au, we use a log-linear model to represent the distri-
Page 3, “Building Dialog Trees from Instructions”
- We employ a log-linear model and try to maximize initial dialog state distribution over the space of all nodes in a dialog network:
Page 5, “Understanding Initial Queries”
- Dialog State Update Model We use a log-linear model to maximize a dialog state distribution over the space of all nodes in a dialog network:
Page 7, “Understanding Query Refinements”
See all papers in Proc. ACL 2013 that mention log-linear model.
See all papers in Proc. ACL that mention log-linear model.
Back to top.