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

by   Arash Eshghi, et al.

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 Facebook AI bAbI dataset even when trained on only 0.13 dialogues). It can in addition process 65 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.


page 1

page 2

page 3

page 4


Bootstrapping incremental dialogue systems: using linguistic knowledge to learn from minimal data

We present a method for inducing new dialogue systems from very small am...

Challenging Neural Dialogue Models with Natural Data: Memory Networks Fail on Incremental Phenomena

Natural, spontaneous dialogue proceeds incrementally on a word-by-word b...

Multi-Task Learning for Domain-General Spoken Disfluency Detection in Dialogue Systems

Spontaneous spoken dialogue is often disfluent, containing pauses, hesit...

Training an adaptive dialogue policy for interactive learning of visually grounded word meanings

We present a multi-modal dialogue system for interactive learning of per...

Semantic Representation for Dialogue Modeling

Although neural models have achieved competitive results in dialogue sys...

Exploring Semantic Incrementality with Dynamic Syntax and Vector Space Semantics

One of the fundamental requirements for models of semantic processing in...

Findings from Experiments of On-line Joint Reinforcement Learning of Semantic Parser and Dialogue Manager with real Users

Design of dialogue systems has witnessed many advances lately, yet acqui...