The DOI matches its Crossref record.
Adaptation of maximum entropy capitalizer: Little data can help a lot
Abstract
A novel technique for maximum “a posteriori” (MAP) adaptation of maximum entropy (MaxEnt) and maximum entropy Markov models (MEMM) is presented. The technique is applied to the problem of automatically capitalizing uniformly cased text. Automatic capitalization is a practically relevant problem: speech recognition output needs to be capitalized; also, modern word processors perform capitalization among other text proofing algorithms such as spelling correction and grammar checking. Capitalization can be also used as a preprocessing step in named entity extraction or machine translation. A “background” capitalizer trained on 20 M words of Wall Street Journal (WSJ) text from 1987 is adapted to two Broadcast News (BN) test sets – one containing ABC Primetime Live text and the other NPR Morning News/CNN Morning Edition text – from 1996. The “in-domain” performance of the WSJ capitalizer is 45% better relative to the 1-gram baseline, when evaluated on a test set drawn from WSJ 1994. When evaluating on the mismatched “out-of-domain” test data, the 1-gram baseline is outperformed by 60% relative; the improvement brought by the adaptation technique using a very small amount of matched BN data – 25–70k words – is about 20–25% relative. Overall, automatic capitalization error rate of 1.4% is achieved on BN data. The performance gain obtained by employing our adaptation technique using a tiny amount of out-of-domain training data on top of the background data is striking: as little as 0.14 M words of in-domain data brings more improvement than using 10 times more background training data (from 2 M words to 20 M words).
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
Cited by
Weiss, K., Khoshgoftaar, T. M., & Wang, D. (2016) · Journal of Big Data · doi:10.1186/s40537-016-0043-6 · Cited by 6,260
(2007) · Cited by 2,018
Domain adaptation with structural correspondence learning
Blitzer, J., McDonald, R., & Pereira, F. (2006) · Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing - EMNLP '06 · doi:10.3115/1610075.1610094 · Cited by 1,543
“In such cases, we must take steps to adapt a model trained on the source domain for use in the target domain (Roark and Bacchiani, 2003; Florian et al., 2004; Chelba and Acero, 2004; Ando, 2004; Lease and Char-niak, 2005; Daum´e III and Marcu, 2006).”
BackgroundMethodInfluentialDomain Adaptation Problems: A DASVM Classification Technique and a Circular Validation Strategy
Bruzzone, L., & Marconcini, M. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.57 · Cited by 591
Domain Adaptation: Learning Bounds and Algorithms
Mansour, Y., Mohri, M., & Rostamizadeh, A. (2009) · arXiv · doi:10.48550/arxiv.0902.3430 · Cited by 504
Machine Learning Paradigms for Speech Recognition: An Overview
Deng, L., & Li, X. (2013) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2013.2244083 · Cited by 456
A survey of multi-source domain adaptation
Sun, S., Shi, H., & Wu, Y. (2015) · Information Fusion · doi:10.1016/j.inffus.2014.12.003 · Cited by 322
Object Recognition in 3D Point Clouds Using Web Data and Domain Adaptation
Lai, K., & Fox, D. (2010) · The International Journal of Robotics Research · doi:10.1177/0278364910369190 · Cited by 152
Neural Structural Correspondence Learning for Domain Adaptation
Ziser, Y., & Reichart, R. (2017) · Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017) · doi:10.18653/v1/k17-1040 · Cited by 122
Natural language generation for sponsored-search advertisements
Bartz, K., Barr, C., & Aijaz, A. (2008) · Proceedings of the 9th ACM conference on Electronic commerce · doi:10.1145/1386790.1386792 · Cited by 21
“Automatic capitalization is important to industry; recent work includes Chelba and Acero[ 4 ].”
Metadata
- Authors
- Chelba, C., & Acero, A.
- Venue
- Computer Speech & Language
- Publisher
- Elsevier BV
- Published
- 2006-10
- Volume
- 20
- Issue
- 4
- Pages
- 382-399
- ISSN
- 0885-2308 (ISSN-L)
- OpenAlex
- W2014703436
- Cited by
- 180
- References
- 0
- FWCI
- 6.18
- Type
- journal article
- Language
- en
- Open access
- closed
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.