Unstructured Knowledge Access in Task-oriented Dialog Modeling using Language Inference, Knowledge Retrieval and Knowledge-Integrative Response Generation

by   Mudit Chaudhary, et al.

Dialog systems enriched with external knowledge can handle user queries that are outside the scope of the supporting databases/APIs. In this paper, we follow the baseline provided in DSTC9 Track 1 and propose three subsystems, KDEAK, KnowleDgEFactor, and Ens-GPT, which form the pipeline for a task-oriented dialog system capable of accessing unstructured knowledge. Specifically, KDEAK performs knowledge-seeking turn detection by formulating the problem as natural language inference using knowledge from dialogs, databases and FAQs. KnowleDgEFactor accomplishes the knowledge selection task by formulating a factorized knowledge/document retrieval problem with three modules performing domain, entity and knowledge level analyses. Ens-GPT generates a response by first processing multiple knowledge snippets, followed by an ensemble algorithm that decides if the response should be solely derived from a GPT2-XL model, or regenerated in combination with the top-ranking knowledge snippet. Experimental results demonstrate that the proposed pipeline system outperforms the baseline and generates high-quality responses, achieving at least 58.77


page 1

page 2

page 3

page 4


Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog

This paper summarizes our work on the first track of the ninth Dialog Sy...

Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems

Task-oriented conversational modeling with unstructured knowledge access...

Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access

Most prior work on task-oriented dialogue systems are restricted to a li...

Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning

Task-oriented dialog presents a difficult challenge encompassing multipl...

Autoregressive Entity Generation for End-to-End Task-Oriented Dialog

Task-oriented dialog (TOD) systems often require interaction with an ext...

Learning to Select External Knowledge with Multi-Scale Negative Sampling

The Track-1 of DSTC9 aims to effectively answer user requests or questio...

Can I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modeling

Most prior work on task-oriented dialogue systems are restricted to limi...