A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning

Yichi Zhang, Zhijian Ou, Min Hu, Junlan Feng

Dialog and Interactive Systems Long Paper

Zoom-16A: Nov 19, Zoom-16A: Nov 19 (00:00-01:00 UTC) [Join Zoom Meeting]

You can open the pre-recorded video in a separate window.

Abstract: Structured belief states are crucial for user goal tracking and database query in task-oriented dialog systems. However, training belief trackers often requires expensive turn-level annotations of every user utterance. In this paper we aim at alleviating the reliance on belief state labels in building end-to-end dialog systems, by leveraging unlabeled dialog data towards semi-supervised learning. We propose a probabilistic dialog model, called the LAtent BElief State (LABES) model, where belief states are represented as discrete latent variables and jointly modeled with system responses given user inputs. Such latent variable modeling enables us to develop semi-supervised learning under the principled variational learning framework. Furthermore, we introduce LABES-S2S, which is a copy-augmented Seq2Seq model instantiation of LABES. In supervised experiments, LABES-S2S obtains strong results on three benchmark datasets of different scales. In utilizing unlabeled dialog data, semi-supervised LABES-S2S significantly outperforms both supervised-only and semi-supervised baselines. Remarkably, we can reduce the annotation demands to 50% without performance loss on MultiWOZ.
NOTE: Video may display a random order of authors. Correct author list is at the top of this page.

Connected Papers in EMNLP2020

Similar Papers

Simple Data Augmentation with the Mask Token Improves Domain Adaptation for Dialog Act Tagging
Semih Yavuz, Kazuma Hashimoto, Wenhao Liu, Nitish Shirish Keskar, Richard Socher, Caiming Xiong,
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
Zhaojiang Lin, Andrea Madotto, Genta Indra Winata, Pascale Fung,
Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions
Bodhisattwa Prasad Majumder, Harsh Jhamtani, Taylor Berg-Kirkpatrick, Julian McAuley,
Augmented Natural Language for Generative Sequence Labeling
Ben Athiwaratkun, Cicero Nogueira dos Santos, Jason Krone, Bing Xiang,