Bootstrapping incremental dialogue systems from minimal data: the
generalisation power of dialogue grammars
release_idqxn2y7f5cwtd2i7hszdwn774
by
Arash Eshghi, Igor Shalyminov, Oliver Lemon
2017
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. 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.
In text/plain
format
Archived Files and Locations
application/pdf 215.2 kB
file_mh6xtjf5lfcuxlftif3hv5snn4
|
arxiv.org (repository) web.archive.org (webarchive) |
1709.07858v1
access all versions, variants, and formats of this works (eg, pre-prints)