Bootstrapping incremental dialogue systems from minimal data: the generalisation power of dialogue grammars

Arash Eshghi, Igor Shalyminov, Oliver Lemon

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

6 Citations (Scopus)
8 Downloads (Pure)

Abstract

We investigate an end-to-end method for automatically inducing task-based dialogue systems from small amounts of unannotated dialogue data. It combines an incremental semantic grammar - Dynamic Syntax and Type Theory with Records (DS-TTR) - with Reinforcement Learning (RL), where language generation and dialogue management are a joint decision problem. The systems thus produced are incremental: dialogues are processed word-by-word, shown previously to be essential in supporting natural, spontaneous dialogue. We hypothesised that the rich linguistic knowledge within the grammar should enable a combinatorially large number of dialogue variations to be processed, even when trained on very few dialogues. Our experiments show that our model can process 74% of the Facebook AI bAbI dataset even when trained on only 0.13% of the data (5 dialogues). It can in addition process 65% of bAbI+, a corpus we created by systematically adding incremental dialogue phenomena such as restarts and self-corrections to bAbI. We compare our model with a state-of-the-art retrieval model, memn2n (Bordes et al., 2017). We find that, in terms of semantic accuracy, memn2n shows very poor robustness to the bAbI+ transformations even when trained on the full bAbI dataset.
Original languageEnglish
Title of host publicationProceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
PublisherAssociation for Computational Linguistics
Pages2220-2230
Number of pages11
ISBN (Electronic)9781945626838
DOIs
Publication statusPublished - Sep 2017
Event2017 Conference on Empirical Methods in Natural Language Processing - Øksnehallen, Copenhagen, Denmark
Duration: 9 Sep 201711 Sep 2017

Conference

Conference2017 Conference on Empirical Methods in Natural Language Processing
Abbreviated titleEMNLP 2017
CountryDenmark
CityCopenhagen
Period9/09/1711/09/17

Fingerprint Dive into the research topics of 'Bootstrapping incremental dialogue systems from minimal data: the generalisation power of dialogue grammars'. Together they form a unique fingerprint.

Cite this