Online adaptation of an attention-based neural network for natural language generation

Abstract : Following some recent propositions to handle natural language generation in spoken dialog systems with long short-term memory recurrent neural network models [1] we first investigate a variant thereof with the objective of a better integration of the attention subnetwork. Then our main objective is to propose and evaluate a framework to adapt the NLG module online through direct interactions with the users. When doing so the basic way is to ask the user to utter an alternative sentence to express a particular dialog act. But then the system has to decide between using an automatic transcription or to ask for a manual transcription. To do so a reinforcement learning approach based on an adversarial bandit scheme is retained. We show that by defining appropriately the rewards as a linear combination of expected payoffs and costs of acquiring the new data provided by the user, a system design can balance between improving the system's performance towards a better match with the user's preferences and the burden associated with it.
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02021901
Contributor : Stéphane Huet <>
Submitted on : Saturday, February 16, 2019 - 9:25:04 PM
Last modification on : Wednesday, May 15, 2019 - 10:12:03 AM
Long-term archiving on : Friday, May 17, 2019 - 3:56:25 PM

File

IS17.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02021901, version 1

Collections

Citation

Matthieu Riou, Bassam Jabaian, Stéphane Huet, Fabrice Lefèvre. Online adaptation of an attention-based neural network for natural language generation. Conference of the International Speech Communication Association (Interspeech), 2017, Stockholm, Sweden. ⟨hal-02021901⟩

Share

Metrics

Record views

28

Files downloads

40