DeepAI AI Chat
Log In Sign Up

Towards Handling Unconstrained User Preferences in Dialogue

by   Suraj Pandey, et al.
Toshiba Information Systems (u.k) Ltd
The Open University

A user input to a schema-driven dialogue information navigation system, such as venue search, is typically constrained by the underlying database which restricts the user to specify a predefined set of preferences, or slots, corresponding to the database fields. We envision a more natural information navigation dialogue interface where a user has flexibility to specify unconstrained preferences that may not match a predefined schema. We propose to use information retrieval from unstructured knowledge to identify entities relevant to a user request. We update the Cambridge restaurants database with unstructured knowledge snippets (reviews and information from the web) for each of the restaurants and annotate a set of query-snippet pairs with a relevance label. We use the annotated dataset to train and evaluate snippet relevance classifiers, as a proxy to evaluating recommendation accuracy. We show that with a pretrained transformer model as an encoder, an unsupervised/supervised classifier achieves a weighted F1 of .661/.856.


page 1

page 2

page 3

page 4


Leveraging Schema Labels to Enhance Dataset Search

A search engine's ability to retrieve desirable datasets is important fo...

A Neural Topical Expansion Framework for Unstructured Persona-oriented Dialogue Generation

Unstructured Persona-oriented Dialogue Systems (UPDS) has been demonstra...

Demonstration of a Multiresolution Schema Mapping System

Enterprise databases usually contain large and complex schemas. Authorin...

Dialogue-to-Video Retrieval

Recent years have witnessed an increasing amount of dialogue/conversatio...

A Fast and Robust BERT-based Dialogue State Tracker for Schema-Guided Dialogue Dataset

Dialog State Tracking (DST) is one of the most crucial modules for goal-...