Bootstrapping dialogue systems: the contribution of a semantic model of interactional dynamics

Arash Eshghi, Igor Shalyminov, Oliver Lemon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We investigate an end-to-end method for automatically inducing task-based dialogue systems from small amounts of unannotated dialogue data. The method combines an incremental, semantic grammar formalism - Dynamic Syntax (DS) and Type Theory with Records (DS-TTR) with Reinforcement Learning (RL), where language generation and dialogue management are treated as one and the same decision problem. The systems thus produced are incremental: dialogues are processed word-by-word, shown in prior work to be essential in supporting more natural, spontaneous dialogue. We hypothesised that given the rich linguistic knowledge present within the grammar, our model should enable a combinatorially large number of interactional variations to be processed, even when the system is trained from only a few dialogues. Our experiments show that our model can process 70% of the Facebook AI bAbI data-set - a set of unannotated dialogues in a ‘restaurant-search’ domain even when trained on only 0.13% of the data-set (5 dialogues). This remarkable generalisation property results from the structural knowledge and constraints present within the grammar, and highlights limitations of recent state-of-the-art systems that are built using machine learning techniques only.
Original languageEnglish
Title of host publicationProceedings of the Conference on Logic and Machine Learning in Natural Language (LaML 2017)
EditorsSimon Dobnik, Shalom Lappin
Pages79-84
Publication statusPublished - Jun 2017
EventConference on Logic and Machine Learning in Natural Language 2017 - Gothenburg, Sweden
Duration: 12 Jun 201713 Jun 2017
https://clasp.gu.se/news-events/conference-on-logic-and-machine-learning-in-natural-language--laml-/

Conference

ConferenceConference on Logic and Machine Learning in Natural Language 2017
Abbreviated titleLaML 2017
CountrySweden
CityGothenburg
Period12/06/1713/06/17
Internet address

Fingerprint Dive into the research topics of 'Bootstrapping dialogue systems: the contribution of a semantic model of interactional dynamics'. Together they form a unique fingerprint.

Cite this