In the automatic evaluation of generative question answering (GenQA) systems, it is difficult to assess the correctness of generated answers due to the free-form of the answer. Especially, widely used n-gram similarity metrics often fail to discriminate the incorrect answers since they equally consider all of the tokens. To alleviate this problem, we propose KPQA-metric, a new metric for evaluating the correctness of GenQA. Specifically, our new metric assigns different weights to each token via keyphrase prediction, thereby judging whether a generated answer sentence captures the key meaning of the reference answer. To evaluate our metric, we create high-quality human judgments of correctness on two GenQA datasets. Using our human-evaluation datasets, we show that our proposed metric has a significantly higher correlation with human judgments than existing metrics. The code is available at https://github.com/hwanheelee1993/KPQA.
KPQA: A Metric for Generative Question Answering Using Keyphrase Weights
A new metric, KPQA-metric, evaluates the correctness of generative question answering by weighting tokens through keyphrase prediction, demonstrating higher correlation with human evaluations compared to existing metrics.
- Year
- 2020
- Venue
- NAACL 2021 4
- Authors
- 7
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2005.00192v3ARXIV-DEFAULT
- TL;DR
- Semantic Scholar