Latent Intention Dialogue Models

Tsung-Hsien Wen, Yishu Miao, Phil Blunsom, Steve Young
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:3732-3741, 2017.

Abstract

Developing a dialogue agent that is capable of making autonomous decisions and communicating by natural language is one of the long-term goals of machine learning research. The traditional approaches either rely on hand-crafting a small state-action set for applying reinforcement learning that is not scalable or constructing deterministic models for learning dialogue sentences that fail to capture the conversational stochasticity. In this paper, however, we propose a Latent Intention Dialogue Model that employs a discrete latent variable to learn underlying dialogue intentions in the framework of neural variational inference. Additionally, in a goal-oriented dialogue scenario, the latent intentions can be interpreted as actions guiding the generation of machine responses, which can be further refined autonomously by reinforcement learning. The experiments demonstrate the effectiveness of discrete latent variable models on learning goal-oriented dialogues, and the results outperform the published benchmarks on both corpus-based evaluation and human evaluation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v70-wen17a, title = {Latent Intention Dialogue Models}, author = {Tsung-Hsien Wen and Yishu Miao and Phil Blunsom and Steve Young}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {3732--3741}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/wen17a/wen17a.pdf}, url = {https://proceedings.mlr.press/v70/wen17a.html}, abstract = {Developing a dialogue agent that is capable of making autonomous decisions and communicating by natural language is one of the long-term goals of machine learning research. The traditional approaches either rely on hand-crafting a small state-action set for applying reinforcement learning that is not scalable or constructing deterministic models for learning dialogue sentences that fail to capture the conversational stochasticity. In this paper, however, we propose a Latent Intention Dialogue Model that employs a discrete latent variable to learn underlying dialogue intentions in the framework of neural variational inference. Additionally, in a goal-oriented dialogue scenario, the latent intentions can be interpreted as actions guiding the generation of machine responses, which can be further refined autonomously by reinforcement learning. The experiments demonstrate the effectiveness of discrete latent variable models on learning goal-oriented dialogues, and the results outperform the published benchmarks on both corpus-based evaluation and human evaluation.} }
Endnote
%0 Conference Paper %T Latent Intention Dialogue Models %A Tsung-Hsien Wen %A Yishu Miao %A Phil Blunsom %A Steve Young %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-wen17a %I PMLR %P 3732--3741 %U https://proceedings.mlr.press/v70/wen17a.html %V 70 %X Developing a dialogue agent that is capable of making autonomous decisions and communicating by natural language is one of the long-term goals of machine learning research. The traditional approaches either rely on hand-crafting a small state-action set for applying reinforcement learning that is not scalable or constructing deterministic models for learning dialogue sentences that fail to capture the conversational stochasticity. In this paper, however, we propose a Latent Intention Dialogue Model that employs a discrete latent variable to learn underlying dialogue intentions in the framework of neural variational inference. Additionally, in a goal-oriented dialogue scenario, the latent intentions can be interpreted as actions guiding the generation of machine responses, which can be further refined autonomously by reinforcement learning. The experiments demonstrate the effectiveness of discrete latent variable models on learning goal-oriented dialogues, and the results outperform the published benchmarks on both corpus-based evaluation and human evaluation.
APA
Wen, T., Miao, Y., Blunsom, P. & Young, S.. (2017). Latent Intention Dialogue Models. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:3732-3741 Available from https://proceedings.mlr.press/v70/wen17a.html.

Related Material