BoK: Introducing Bag-of-Keywords Loss for Interpretable Dialogue Response Generation

TL;DR

This paper introduces the Bag-of-Keywords (BoK) loss, an auxiliary training method that improves dialogue response relevance and interpretability by focusing on key words, enhancing existing models and evaluation metrics.

Contribution

The paper proposes the novel BoK loss that predicts core keywords to improve response quality and interpretability in dialogue systems, applicable to encoder-decoder and decoder-only architectures.

Findings

BoK loss enhances dialogue generation quality.

BoK loss enables post-hoc interpretability.

BoK-LM as a reference-free evaluation metric performs comparably to state-of-the-art metrics.

Abstract

The standard language modeling (LM) loss by itself has been shown to be inadequate for effective dialogue modeling. As a result, various training approaches, such as auxiliary loss functions and leveraging human feedback, are being adopted to enrich open-domain dialogue systems. One such auxiliary loss function is Bag-of-Words (BoW) loss, defined as the cross-entropy loss for predicting all the words/tokens of the next utterance. In this work, we propose a novel auxiliary loss named Bag-of-Keywords (BoK) loss to capture the central thought of the response through keyword prediction and leverage it to enhance the generation of meaningful and interpretable responses in open-domain dialogue systems. BoK loss upgrades the BoW loss by predicting only the keywords or critical words/tokens of the next utterance, intending to estimate the core idea rather than the entire response. We incorporate BoK loss in both encoder-decoder (T5) and decoder-only (DialoGPT) architecture and train the models to minimize the weighted sum of BoK and LM (BoK-LM) loss. We perform our experiments on two popular open-domain dialogue datasets, DailyDialog and Persona-Chat. We show that the inclusion of BoK loss improves the dialogue generation of backbone models while also enabling post-hoc interpretability. We also study the effectiveness of BoK-LM loss as a reference-free metric and observe comparable performance to the state-of-the-art metrics on various dialogue evaluation datasets.