DialoGen: Generalized Long-Range Context Representation for Dialogue Systems

TL;DR

DialoGen introduces a novel dialogue context representation framework that identifies and utilizes the most relevant historical utterances, enabling better long-range dependency modeling and compact dialogue history encoding.

Contribution

The paper presents DialoGen, a new encoder-decoder framework that improves dialogue understanding and generation by focusing on relevant past utterances beyond the last-$k$, enhancing long-range context modeling.

Findings

DialoGen performs comparably to state-of-the-art models on DailyDialog.

It achieves similar results on MultiWOZ for dialogue state tracking.

Relevance scores align well with human judgment.

Abstract

Long-range context modeling is crucial to both dialogue understanding and generation. The most popular method for dialogue context representation is to concatenate the last-$k$ utterances in chronological order. However, this method may not be ideal for conversations containing long-range dependencies, i.e., when there is a need to look beyond last-$k$ utterances to generate a meaningful response. In this work, we propose DialoGen, a novel encoder-decoder based framework for dialogue generation with a generalized context representation that can look beyond the last-$k$ utterances. The main idea of our approach is to identify and utilize the most relevant historical utterances instead of last-$k$, which also enables the compact representation of dialogue history with fewer tokens. We study the effectiveness of our proposed method on both dialogue generation (open-domain) and understanding (DST). Even with a compact context representation, DialoGen performs comparably to the state-of-the-art models on the open-domain DailyDialog dataset. We observe a similar behavior on the DST task of the MultiWOZ dataset when the proposed context representation is applied to existing DST models. We also discuss the generalizability and interpretability of DialoGen and show that the relevance score of previous utterances agrees well with human cognition.