Task-Oriented Dialogue as Dataflow Synthesis
- URL: http://arxiv.org/abs/2009.11423v3
- Date: Thu, 11 Feb 2021 00:10:56 GMT
- Title: Task-Oriented Dialogue as Dataflow Synthesis
- Authors: Semantic Machines, Jacob Andreas, John Bufe, David Burkett, Charles
Chen, Josh Clausman, Jean Crawford, Kate Crim, Jordan DeLoach, Leah Dorner,
Jason Eisner, Hao Fang, Alan Guo, David Hall, Kristin Hayes, Kellie Hill,
Diana Ho, Wendy Iwaszuk, Smriti Jha, Dan Klein, Jayant Krishnamurthy, Theo
Lanman, Percy Liang, Christopher H Lin, Ilya Lintsbakh, Andy McGovern,
Aleksandr Nisnevich, Adam Pauls, Dmitrij Petters, Brent Read, Dan Roth,
Subhro Roy, Jesse Rusak, Beth Short, Div Slomin, Ben Snyder, Stephon
Striplin, Yu Su, Zachary Tellman, Sam Thomson, Andrei Vorobev, Izabela
Witoszko, Jason Wolfe, Abby Wray, Yuchen Zhang, Alexander Zotov
- Abstract summary: We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph.
A dialogue agent maps each user utterance to a program that extends this graph.
We introduce a new dataset, SMCalFlow, featuring complex dialogues about events, weather, places, and people.
- Score: 158.77123205487334
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We describe an approach to task-oriented dialogue in which dialogue state is
represented as a dataflow graph. A dialogue agent maps each user utterance to a
program that extends this graph. Programs include metacomputation operators for
reference and revision that reuse dataflow fragments from previous turns. Our
graph-based state enables the expression and manipulation of complex user
intents, and explicit metacomputation makes these intents easier for learned
models to predict. We introduce a new dataset, SMCalFlow, featuring complex
dialogues about events, weather, places, and people. Experiments show that
dataflow graphs and metacomputation substantially improve representability and
predictability in these natural dialogues. Additional experiments on the
MultiWOZ dataset show that our dataflow representation enables an otherwise
off-the-shelf sequence-to-sequence model to match the best existing
task-specific state tracking model. The SMCalFlow dataset and code for
replicating experiments are available at
https://www.microsoft.com/en-us/research/project/dataflow-based-dialogue-semantic-machines.
Related papers
- Unsupervised Flow Discovery from Task-oriented Dialogues [0.988655456942026]
We propose an approach for the unsupervised discovery of flows from dialogue history.
We present concrete examples of flows, discovered from MultiWOZ, a public TOD dataset.
arXiv Detail & Related papers (2024-05-02T15:54:36Z) - TimeGraphs: Graph-based Temporal Reasoning [64.18083371645956]
TimeGraphs is a novel approach that characterizes dynamic interactions as a hierarchical temporal graph.
Our approach models the interactions using a compact graph-based representation, enabling adaptive reasoning across diverse time scales.
We evaluate TimeGraphs on multiple datasets with complex, dynamic agent interactions, including a football simulator, the Resistance game, and the MOMA human activity dataset.
arXiv Detail & Related papers (2024-01-06T06:26:49Z) - TOD-Flow: Modeling the Structure of Task-Oriented Dialogues [77.15457469745364]
We propose a novel approach focusing on inferring the TOD-Flow graph from dialogue data annotated with dialog acts.
The inferred TOD-Flow graph can be easily integrated with any dialogue model to improve its prediction performance, transparency, and controllability.
arXiv Detail & Related papers (2023-12-07T20:06:23Z) - Dataflow Dialogue Generation [0.0]
We show an example of agenda driven dialogue generation for the MultiWOZ domain, and an example of generation without an agenda for the SMCalFlow domain.
We show an improvement in the accuracy of the translation of user requests to dataflow expressions when the generated dialogues are used to augment the translation training dataset.
arXiv Detail & Related papers (2023-08-04T13:40:54Z) - Conversational Semantic Parsing using Dynamic Context Graphs [68.72121830563906]
We consider the task of conversational semantic parsing over general purpose knowledge graphs (KGs) with millions of entities, and thousands of relation-types.
We focus on models which are capable of interactively mapping user utterances into executable logical forms.
arXiv Detail & Related papers (2023-05-04T16:04:41Z) - Turning Flowchart into Dialog: Augmenting Flowchart-grounded
Troubleshooting Dialogs via Synthetic Data Generation [50.06143883455979]
Flowchart-grounded troubleshooting dialogue (FTD) systems follow the instructions of a flowchart to diagnose users' problems in specific domains.
We propose a plan-based synthetic data generation approach that generates diverse synthetic dialog data at scale.
arXiv Detail & Related papers (2023-05-02T11:08:27Z) - DFEE: Interactive DataFlow Execution and Evaluation Kit [15.437150666291457]
We present DFEE, an interactive DataFlow Execution and Evaluation toolkit.
We demonstrate a complex dialog task: event scheduling that involves temporal reasoning.
To illustrate how to benchmark SoTA models, we propose a novel benchmark that covers more sophisticated event scheduling scenarios.
arXiv Detail & Related papers (2022-12-04T23:44:34Z) - Enel: Context-Aware Dynamic Scaling of Distributed Dataflow Jobs using
Graph Propagation [52.9168275057997]
This paper presents Enel, a novel dynamic scaling approach that uses message propagation on an attributed graph to model dataflow jobs.
We show that Enel is able to identify effective rescaling actions, reacting for instance to node failures, and can be reused across different execution contexts.
arXiv Detail & Related papers (2021-08-27T10:21:08Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.