Pith. sign in

REVIEW 1 cited by

Unsupervised Dialog Structure Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1904.03736 v2 pith:SLWNDDMR submitted 2019-04-07 cs.CL cs.AI

classification cs.CLcs.AI
keywords dialogmodelstructuredialogslearningdesignlearnedmodels
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Learning a shared dialog structure from a set of task-oriented dialogs is an important challenge in computational linguistics. The learned dialog structure can shed light on how to analyze human dialogs, and more importantly contribute to the design and evaluation of dialog systems. We propose to extract dialog structures using a modified VRNN model with discrete latent vectors. Different from existing HMM-based models, our model is based on variational-autoencoder (VAE). Such model is able to capture more dynamics in dialogs beyond the surface forms of the language. We find that qualitatively, our method extracts meaningful dialog structure, and quantitatively, outperforms previous models on the ability to predict unseen data. We further evaluate the model's effectiveness in a downstream task, the dialog system building task. Experiments show that, by integrating the learned dialog structure into the reward function design, the model converges faster and to a better outcome in a reinforcement learning setting.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. How to Build User Simulators to Train RL-based Dialog Systems

    cs.CL 2019-09 conditional novelty 5.0 of 10

    A comparison of six user simulators for training RL dialog systems finds that agenda-based simulators yield systems humans rate higher, and that a single simulator's automatic success rate does not predict real-user s...

Pith tools