REAM: An Enhancement Approach to Reference-based Evaluation Metrics for Open-domain Dialog Generation
arXiv:2105.14488
Abstract
The lack of reliable automatic evaluation metrics is a major impediment to the development of open-domain dialogue systems. Various reference-based metrics have been proposed to calculate a score between a predicted response and a small set of references. However, these metrics show unsatisfactory correlations with human judgments. For a reference-based metric, its reliability mainly depends on two factors: its ability to measure the similarity between the predicted response and the reference response, as well as the reliability of the given reference set. Yet, there are few discussions on the latter. Our work attempts to fill this vacancy. We first clarify an assumption on reference-based metrics that, if more high-quality references are added into the reference set, the reliability of the metric will increase. Next, we present REAM: an enhancement approach to Reference-based EvAluation Metrics for open-domain dialogue systems. A prediction model is designed to estimate the reliability of the given reference set. We show how its predicted results can be helpful to augment the reference set, and thus improve the reliability of the metric. Experiments validate both the effectiveness of our prediction model and that the reliability of reference-based metrics improves with the augmented reference sets.
arXiv commentACL Findings 2021
References in corpus (9)
- Convolutional Sequence to Sequence Learning
- How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
- A Simple, Fast Diverse Decoding Algorithm for Neural Generation
- Adversarial Learning for Neural Dialogue Generation
- RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems
- Mutual Information and Diverse Decoding Improve Neural Machine Translation
- Better Automatic Evaluation of Open-Domain Dialogue Systems with Contextualized Embeddings
- GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems
- Fine-Grained Sentence Functions for Short-Text Conversation