AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue

TL;DR

This paper introduces AMUSED, a multi-stream deep learning architecture that combines semantic, syntactic, and external knowledge to generate more coherent and engaging conversational responses.

Contribution

It presents a novel multi-stream model integrating memory networks, GCNs, transfer learning, and KBs for improved dialogue response generation.

Findings

Significantly outperforms existing methods on next sentence prediction.

Enhances dialogue coherence and engagement in retrieval-based agents.

Validated by expert linguists for comprehensive human interaction.

Abstract

The problem of building a coherent and non-monotonous conversational agent with proper discourse and coverage is still an area of open research. Current architectures only take care of semantic and contextual information for a given query and fail to completely account for syntactic and external knowledge which are crucial for generating responses in a chit-chat system. To overcome this problem, we propose an end to end multi-stream deep learning architecture which learns unified embeddings for query-response pairs by leveraging contextual information from memory networks and syntactic information by incorporating Graph Convolution Networks (GCN) over their dependency parse. A stream of this network also utilizes transfer learning by pre-training a bidirectional transformer to extract semantic representation for each input sentence and incorporates external knowledge through the the neighborhood of the entities from a Knowledge Base (KB). We benchmark these embeddings on next sentence prediction task and significantly improve upon the existing techniques. Furthermore, we use AMUSED to represent query and responses along with its context to develop a retrieval based conversational agent which has been validated by expert linguists to have comprehensive engagement with humans.