Hierarchical Transformer for Task Oriented Dialog Systems

TL;DR

This paper introduces a generalized hierarchical transformer framework for task-oriented dialog systems, improving context understanding by adapting standard transformers with specialized attention masks and positional encodings.

Contribution

It presents a novel framework that transforms standard transformers into hierarchical encoders, enhancing dialog context modeling in task-oriented systems.

Findings

Hierarchical transformers outperform standard models in context understanding.

The framework unifies various hierarchical models like HRED and HIBERT.

Experiments show improved natural language understanding in dialog tasks.

Abstract

Generative models for dialog systems have gained much interest because of the recent success of RNN and Transformer based models in tasks like question answering and summarization. Although the task of dialog response generation is generally seen as a sequence-to-sequence (Seq2Seq) problem, researchers in the past have found it challenging to train dialog systems using the standard Seq2Seq models. Therefore, to help the model learn meaningful utterance and conversation level features, Sordoni et al. (2015b); Serban et al. (2016) proposed Hierarchical RNN architecture, which was later adopted by several other RNN based dialog systems. With the transformer-based models dominating the seq2seq problems lately, the natural question to ask is the applicability of the notion of hierarchy in transformer based dialog systems. In this paper, we propose a generalized framework for Hierarchical Transformer Encoders and show how a standard transformer can be morphed into any hierarchical encoder, including HRED and HIBERT like models, by using specially designed attention masks and positional encodings. We demonstrate that Hierarchical Encoding helps achieve better natural language understanding of the contexts in transformer-based models for task-oriented dialog systems through a wide range of experiments.