An official website of the United States government
The uncertainty in modeling emotions makes speech emotion recognition (SER) systems less reliable. An intuitive way to increase trust in SER is to reject predictions with low confidence. This approach assumes that an SER system is well calibrated, where highly confident predictions are often right and low confident predictions are often wrong. Hence, it is desirable to calibrate the confidence of SER classifiers. We evaluate the reliability of SER systems by exploring the relationship between confidence and accuracy, using the expected calibration error (ECE) metric. We develop a multi-label variant of the post-hoc temperature scaling (TS) method to calibrate SER systems, while preserving their accuracy. The best method combines an emotion co-occurrence weight penalty function, a class-balanced objective function, and the proposed multi-label TS calibration method. The experiments show the effectiveness of our developed multi-label calibration method in terms of ac- curacy and ECE.
more »
« less
Re-Examining Calibration: The Case of Question Answering
For users to trust model predictions, they need to understand model outputs, particularly their confidence — calibration aims to adjust (calibrate) models’ confidence to match expected accuracy. We argue that the traditional calibration evaluation does not promote effective calibrations: for example, it can encourage always assigning a mediocre confidence score to all predictions, which does not help users distinguish correct predictions from wrong ones. Building on those observations, we propose a new calibration metric, MacroCE, that better captures whether the model assigns low confidence to wrong predictions and high confidence to correct predictions. Focusing on the practical application of open-domain question answering, we examine conventional calibration methods applied on the widely-used retriever-reader pipeline, all of which do not bring significant gains under our new MacroCE metric. Toward better calibration, we propose a new calibration method (ConsCal) that uses not just final model predictions but whether multiple model checkpoints make consistent predictions. Altogether, we provide an alternative view of calibration along with a new metric, re-evaluation of existing calibration methods on our metric, and proposal of a more effective calibration method.
more »
« less
- Award ID(s):
- 1822494
- PAR ID:
- 10451418
- Date Published:
- Journal Name:
- Findings of the Association for Computational Linguistics: EMNLP 2022
- Page Range / eLocation ID:
- 2814 to 2829
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Training a machine learning model with data following a meaningful order, i.e., from easy to hard, has been proven to be effective in accelerating the training process and achieving better model performance. The key enabling technique is curriculum learning (CL), which has seen great success and has been deployed in areas like image and text classification. Yet, how CL affects the privacy of machine learning is unclear. Given that CL changes the way a model memorizes the training data, its influence on data privacy needs to be thoroughly evaluated. To fill this knowledge gap, we perform the first study and leverage membership inference attack (MIA) and attribute inference attack (AIA) as two vectors to quantify the privacy leakage caused by CL. Our evaluation of 9 real-world datasets with attack methods (NN-based, metric-based, label-only MIA, and NN-based AIA) revealed new insights about CL. First, MIA becomes slightly more effective when CL is applied, but the impact is much more prominent to a subset of training samples ranked as difficult. Second, a model trained under CL is less vulnerable under AIA, compared to MIA. Third, the existing defense techniques like MemGuard and MixupMMD are not effective under CL. Finally, based on our insights into CL, we propose a new MIA, termed Diff-Cali, which exploits the difficulty scores for result calibration and is demonstrated to be effective against all CL methods and the normal training method. With this study, we hope to draw the community's attention to the unintended privacy risks of emerging machine-learning techniques and develop new attack benchmarks and defense solutions.more » « less
-
As AI use becomes more common, it's important to measure not just whether the systems are correct but whether they know when they're incorrect. We propose a new metric to measure this mismatch between correctness and confidence, compare computer ability with human ability, and show that computers have a long way to go before they're well-calibrated.more » « less
-
null (Ed.)To address the lack of comparative evaluation of Human-in-the-Loop Topic Modeling (HLTM) systems, we implement and evaluate three contrasting HLTM modeling approaches using simulation experiments. These approaches extend previously proposed frameworks, including constraints and informed prior-based methods. Users should have a sense of control in HLTM systems, so we propose a control metric to measure whether refinement operations’ results match users’ expectations. Informed prior-based methods provide better control than constraints, but constraints yield higher quality topics.more » « less
-
To build robust question answering systems, we need the ability to verify whether answers to questions are truly correct, not just “good enough” in the context of imperfect QA datasets. We explore the use of natural language inference (NLI) as a way to achieve this goal, as NLI inherently requires the premise (document context) to contain all necessary information to support the hypothesis (proposed answer to the question). We leverage large pre-trained models and recent prior datasets to construct powerful question conversion and decontextualization modules, which can reformulate QA instances as premise-hypothesis pairs with very high reliability. Then, by combining standard NLI datasets with NLI examples automatically derived from QA training data, we can train NLI models to evaluate QA models’ proposed answers. We show that our approach improves the confidence estimation of a QA model across different domains, evaluated in a selective QA setting. Careful manual analysis over the predictions of our NLI model shows that it can further identify cases where the QA model produces the right answer for the wrong reason, i.e., when the answer sentence cannot address all aspects of the question.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.18653/v1/2022.findings-emnlp.204
