Improving nonparameteric Bayesian inference: experiments on unsupervised word segmentation with adaptor grammars
Open accessThe DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
One of the reasons nonparametric Bayesian inference is attracting attention in computational linguistics is because it provides a principled way of learning the units of generalization together with their probabilities. Adaptor grammars are a framework for defining a variety of hierarchical nonparametric Bayesian models. This paper investigates some of the choices that arise in formulating adaptor grammars and associated inference procedures, and shows that they can have a dramatic impact on performance in an unsupervised word segmentation task. With appropriate adaptor grammars and inference procedures we achieve an 87% word token f-score on the standard Brent version of the Bernstein-Ratner corpus, which is an error reduction of over 35% over the best previously reported results for this corpus.
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.
Integrity signals
Registry
Cites
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.
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
Elman, J. L. (1990) · Cognitive Science · doi:10.1207/s15516709cog1402_1 · Cited by 11,212
Distributional regularity and phonotactic constraints are useful for segmentation
Brent, M. R., & Cartwright, T. A. (1996) · Cognition · doi:10.1016/s0010-0277(96)00719-6 · Cited by 514 · cited 3×
“…grammar performs unsupervised word segmentation with an 87% token f-score on the standard Brent version of the Bernstein-Ratner corpus (Bernstein-Ratner, 1987; Brent and Cartwright, 1996), which is an error reduction of over 35% compared to the best previously reported results on this corpus.”
MethodResultInfluential
Cited by
Symbol emergence in robotics: a survey
Taniguchi, T., Nagai, T., Nakamura, T., Iwahashi, N., Ogata, T., & Asoh, H. (2016) · Advanced Robotics · doi:10.1080/01691864.2016.1164622 · Cited by 150
Decolonising Speech and Language Technology
Bird, S. (2020) · Proceedings of the 28th International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.313 · Cited by 151
Word Segmentation on Discovered Phone Units With Dynamic Programming and Self-Supervised Scoring
Kamper, H. (2023) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2022.3229264 · Cited by 24
“speech, the speech is encoded according to the most probable component for each MFCC frame, repeated components are merged, and the resulting tokenization is segmented with an adaptor grammar [3].”
MethodInfluential
Metadata
- Authors
- Johnson, M., & Goldwater, S.
- Venue
- Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics on - NAACL '09
- Published
- 2009
- Pages
- 317
- OpenAlex
- W2126449874
- Cited by
- 118
- References
- 2
- FWCI
- 8.70
- Type
- conference paper
- Language
- en
- Open access
- gold
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.