CoChat

Incorporating Uncertainty into Deep Learning for Spoken Language Assessment

Open access
Malinin, Andrey, Ragni, Anton, Knill, Kate, Gales, Mark · 2017 · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

The DOI matches its Crossref record; 14 of the 16 references it cites were found in a registry or an index.

Abstract

There is a growing demand for automatic assessment of spoken English proficiency.These systems need to handle large variations in input data owing to the wide range of candidate skill levels and L1s, and errors from ASR.Some candidates will be a poor match to the training data set, undermining the validity of the predicted grade.For high stakes tests it is essential for such systems not only to grade well, but also to provide a measure of their uncertainty in their predictions, enabling rejection to human graders.Previous work examined Gaussian Process (GP) graders which, though successful, do not scale well with large data sets.Deep Neural Networks (DNN) may also be used to provide uncertainty using Monte-Carlo Dropout (MCD).This paper proposes a novel method to yield uncertainty and compares it to GPs and DNNs with MCD.The proposed approach explicitly teaches a DNN to have low uncertainty on training data and high uncertainty on generated artificial data.On experiments conducted on data from the Business Language Testing Service (BULATS), the proposed approach is found to outperform GPs and DNNs with MCD in uncertainty-based rejection whilst achieving comparable grading performance.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/p17-2008

Cites

14 of 14 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 2

  1. Diederik P. Kingma and Max Welling. 2014. Autoencoding variational bayes. In Proceedings of the 2nd International Conference on Learning Representations (ICLR) .
  2. Kevin P. Murphy. 2012. Machine Learning . The MIT Press.

Cited by

See all 30

Metadata

Authors
Malinin, A., Ragni, A., Knill, K., & Gales, M.
Affiliations
University of Cambridge (GB)
Corresponding author
Knill, Kate
Venue
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Published
2017
Pages
45-50
ISSN
0736-587X (ISSN-L)
OpenAlex
W2739575494
Cited by
29
References
16
Citations by year
2026: 3 · 2025: 2 · 2024: 2 · 2023: 4 · 2021: 6 · 2020: 4 · 2019: 3 · 2018: 4 · 2017: 1
FWCI
1.50
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
  • White Rose Research Online (University of Leeds, The University of Sheffield, University of York) (submittedVersion)
  • Cambridge University Engineering Department Publications Database (submittedVersion)
  • Apollo (University of Cambridge) (submittedVersion)
  • Apollo
Funders
Engineering and Physical Sciences Research Council (1464018)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
  • Social Sciences › Arts and Humanities › Language and Linguistics › EFL/ESL Teaching and Learning
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
Keywords
uncertainty estimation, deep neural network, Monte Carlo dropout, Gaussian process regression, speech recognition errors, out-of-distribution data, high-stakes testing

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.