An official website of the United States government
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
The Importance of Calibration: Rethinking Confidence and Performance of Speech Multi-label Emotion Classifiers
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
- Award ID(s):
- 2016719
- PAR ID:
- 10441271
- Date Published:
- Journal Name:
- Interspeech 2023
- Page Range / eLocation ID:
- 641 to 645
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
A method to improve protein function prediction for sparsely annotated PPI networks is introduced. The method extends the DSD majority vote algorithm introduced by Cao et al. to give confidence scores on predicted labels and to use predictions of high confidence to predict the labels of other nodes in subsequent rounds. We call this a majority vote cascade. Several cascade variants are tested in a stringent cross-validation experiment on PPI networks from S. cerevisiae and D. melanogaster, and we show that for many different settings with several alternative confidence functions, cascading improves the accuracy of the predictions. A list of the most confident new label predictions in the two networks is also reported. Code and networks for the cross-validation experiments appear at http://bcb.cs.tufts.edu/cascade.more » « less
-
A method to improve protein function prediction for sparsely annotated PPI networks is introduced. The method extends the DSD majority vote algorithm introduced by Cao et al. to give confidence scores on predicted labels and to use predictions of high confidence to predict the labels of other nodes in subsequent rounds. We call this a majority vote cascade. Several cascade variants are tested in a stringent cross-validation experiment on PPI networks from S. cerevisiae and D. melanogaster, and we show that for many different settings with several alternative confidence functions, cascading improves the accuracy of the predictions. A list of the most confident new label predictions in the two networks is also reported. Code, networks for the cross-validation experiments, and supplementary figures and tables appear at http://bcb.cs.tufts.edu/cascade.more » « less
-
null (Ed.)Speech emotion recognition (SER) plays an important role in multiple fields such as healthcare, human-computer interaction (HCI), and security and defense. Emotional labels are often annotated at the sentence-level (i.e., one label per sentence), resulting in a sequence-to-one recognition problem. Traditionally, studies have relied on statistical descriptions, which are com- puted over time from low level descriptors (LLDs), creating a fixed dimension sentence-level feature representation regardless of the duration of the sentence. However sentence-level features lack temporal information, which limits the performance of SER systems. Recently, new deep learning architectures have been proposed to model temporal data. An important question is how to extract emotion-relevant features with temporal infor- mation. This study proposes a novel data processing approach that extracts a fixed number of small chunks over sentences of different durations by changing the overlap between these chunks. The approach is flexible, providing an ideal frame- work to combine gated network or attention mechanisms with long short-term memory (LSTM) networks. Our experimental results based on the MSP-Podcast dataset demonstrate that the proposed method not only significantly improves recognition accuracy over alternative temporal-based models relying on LSTM, but also leads to computational efficiency.more » « less
-
Previous studies on speech emotion recognition (SER) with categorical emotions have often formulated the task as a single-label classification problem, where the emotions are considered orthogonal to each other. However, previous studies have indicated that emotions can co-occur, especially for more ambiguous emotional sentences (e.g., a mixture of happiness and sur- prise). Some studies have regarded SER problems as a multi-label task, predicting multiple emotional classes. However, this formulation does not leverage the relation between emotions during training, since emotions are assumed to be independent. This study explores the idea that emotional classes are not necessarily independent and its implications on training SER models. In particular, we calculate the frequency of co-occurring emotions from perceptual evaluations in the train set to generate a matrix with class-dependent penalties, punishing more mistakes between distant emotional classes. We integrate the penalization matrix into three existing label-learning approaches (hard-label, multi-label, and distribution-label learn- ing) using the proposed modified loss. We train SER models using the penalty loss and commonly used cost functions for SER tasks. The evaluation of our proposed penalization matrix on the MSP-Podcast corpus shows important relative improvements in macro F1-score for hard-label learning (17.12%), multi-label learning (12.79%), and distribution-label learning (25.8%).more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.21437/Interspeech.2023-1113
