Augmenting Transformers with KNN-Based Composite Memory for Dialogue

04/27/2020
by   Angela Fan, et al.
0

Various machine learning tasks can benefit from access to external information of different modalities, such as text and images. Recent work has focused on learning architectures with large memories capable of storing this knowledge. We propose augmenting generative Transformer neural networks with KNN-based Information Fetching (KIF) modules. Each KIF module learns a read operation to access fixed external knowledge. We apply these modules to generative dialogue modeling, a challenging task where information must be flexibly retrieved and incorporated to maintain the topic and flow of conversation. We demonstrate the effectiveness of our approach by identifying relevant knowledge from Wikipedia, images, and human-written dialogue utterances, and show that leveraging this retrieved information improves model performance, measured by automatic and human evaluation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/28/2022

SINC: Service Information Augmented Open-Domain Conversation

Generative open-domain dialogue systems can benefit from external knowle...
research
06/12/2022

Grounding in social media: An approach to building a chit-chat dialogue model

Building open-domain dialogue systems capable of rich human-like convers...
research
09/15/2020

Unsupervised Abstractive Dialogue Summarization for Tete-a-Tetes

High-quality dialogue-summary paired data is expensive to produce and do...
research
05/01/2018

Memory-augmented Dialogue Management for Task-oriented Dialogue Systems

Dialogue management (DM) decides the next action of a dialogue system ac...
research
11/02/2022

PLATO-K: Internal and External Knowledge Enhanced Dialogue Generation

Recently, the practical deployment of open-domain dialogue systems has b...
research
10/09/2020

On Task-Level Dialogue Composition of Generative Transformer Model

Task-oriented dialogue systems help users accomplish tasks such as booki...
research
06/20/2021

Do Encoder Representations of Generative Dialogue Models Encode Sufficient Information about the Task ?

Predicting the next utterance in dialogue is contingent on encoding of u...

Please sign up or login with your details

Forgot password? Click here to reset