[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/aclbulk-2007-goldberg-svm-model-tampering-anchored-learning/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [Modern Hebrew](https://md.mova.elamur.ai/free/en/docs/papers/he/) / SVM Model Tampering and Anchored Learning: A Case Study in Hebrew NP Chunking

# SVM Model Tampering and Anchored Learning: A Case Study in Hebrew NP Chunking

**Authors:** [Yoav Goldberg](https://md.mova.elamur.ai/free/en/docs/papers/authors/yoav-goldberg/); [Michael Elhadad](https://md.mova.elamur.ai/free/en/docs/papers/authors/michael-elhadad/) · **Year:** 2007 · **Venue:** Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics **Link:** [aclanthology.org/P07-1029](https://aclanthology.org/P07-1029/) · library `aclbulk-2007-goldberg-svm-model-tampering-anchored-learning` · **Licence:** [CC BY-NC-SA 3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/) (ACL Anthology, before 2016) — summary only

[**9** citations](https://openalex.org/works?filter=cites:W2141175378) openalex-snapshot · 2026-10-14[**5** citations in our library](https://md.mova.elamur.ai/free/en/docs/papers/cited-by/aclbulk-2007-goldberg-svm-model-tampering-anchored-learning/) of the 140673 papers whose bibliographies we read[Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics](https://aclanthology.org/volumes/P07-1/)[licence](https://creativecommons.org/licenses/by-nc-sa/3.0/)

- [Publisher's page](https://aclanthology.org/P07-1029/)
- [PDF](https://aclanthology.org/P07-1029.pdf)
- [OpenAlex](https://openalex.org/W2141175378)

**Authors (2)**

1. [Yoav Goldberg](https://openalex.org/A5028476919) [ORCID](https://orcid.org/0000-0002-6497-829X) · [Semantic Scholar](https://www.semanticscholar.org/author/2089067) · h 59 · 23282 citations · 401 works
2. [Michael Elhadad](https://openalex.org/A5013658527) [ORCID](https://orcid.org/0000-0002-5629-2351) · [Semantic Scholar](https://www.semanticscholar.org/author/1754680) · h 25 · 3571 citations · 137 works

Citations and author metrics from openalex-snapshot (2026-10-14); authors with the same name are not always told apart.

## What it is about

The paper studies an SVM chunker for Hebrew Simple NPs (about 4,500 training sentences, 500 test, 27K chunks) and opens the trained model in two ways. Model tampering zeroes features in the support vectors after training; keeping only the top 500 of about 30,000 lexical features gives F 93.60 against 93.58 for all of them. Keeping only the top 10 drops F to 78.32 with none and to 90.21 with ten. Lexical features matter most for prepositions, punctuation and the conjunction; features for open classes add little. Anchored learning gives every training sample its own feature, so the SVM can memorise hard cases; the heaviest anchors point at corpus errors. Of about 120 flagged locations, more than half were real errors, and 77 of 99 further similar locations were errors too. Punctuation normalisation adds about 1 F point, and a 10-fold run on the noisy tagger output reaches F 92.2.

## Ideas

- I1. Anchor-weight mining as a corpus audit for Hebrew: train with one unique anchor per sentence, rank the locations by anchor weight, and review the top ones by hand. Record the yield of real errors per reviewed location.
- I2. Keep lexical features only for the closed classes (prepositions, the conjunction "and", punctuation) in any rule-based Hebrew NP or chunk rule, and test by removing the open-class lexicon on noisy tagging. The paper reports that such a small lexical set is enough on gold tags and collapses on noisy tags, so the test must use noisy tags.
- I3. Normalise punctuation inside gold NP spans before scoring, and report the score with and without the normalisation.

## For Mova

I1 is an audit step for `treebanks/he/` and `treebanks/hbo/ptnk`, run after the tree conversion. I2 belongs to the preposition and conjunction rules in [Prepositions, prefixes, conjunctions and particles](https://md.mova.elamur.ai/free/en/docs/languages/he/06-prepositions-particles/) and [The verb](https://md.mova.elamur.ai/free/en/docs/languages/hbo/06-verb/) (the wa- conjunction). I3 goes into the scorer of `tools/macula compare`. The "et" marker and the "shel" attachment cases in the paper are open questions for [7. Syntax](https://md.mova.elamur.ai/free/en/docs/languages/he/07-syntax/).

## Cite

The paper itself, not this card. BibTeX from the library's record of the work.

```
@inproceedings{goldberg2007svm,
  title = {{SVM Model Tampering and Anchored Learning: A Case Study in Hebrew NP Chunking}},
  author = {Goldberg, Yoav and Elhadad, Michael},
  booktitle = {Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics},
  year = {2007},
  url = {https://aclanthology.org/P07-1029/}
}
```

- [← previous Integrated Morphological and Syntactic Disambiguation for Modern Hebrew](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2006-tsarfaty-integrated-morphological-syntactic-disambiguation-modern/)
- [next → Smoothing a Lexicon-based POS Tagger for Arabic and Hebrew](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2007-manour-smoothing-lexicon-based-pos-tagger/)
- [↑ back to Modern Hebrew](https://md.mova.elamur.ai/free/en/docs/papers/he/)

## References

11 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. S. Abney, R. Schapire, and Y. Singer. 1999. Boosting applied to tagging and PP attachment. EMNLP-1999. [find](https://scholar.google.com/scholar?q=S%2E+Abney%2C+R%2E+Schapire%2C+and+Y%2E+Singer%2E+1999%2E+Boosting+applied+to+tagging+and+PP+attachment%2E+EMNLP%2D1999%2E)
2. M. Adler and M. Elhadad. 2006. An unsupervised morpheme-based hmm for hebrew morphological disambiguation. In COLING/ACL2006. [find](https://scholar.google.com/scholar?q=M%2E+Adler+and+M%2E+Elhadad%2E+2006%2E+An+unsupervised+morpheme%2Dbased+hmm+for+hebrew+morphological+disambiguation%2E+In+COLING%2FACL2006%2E) [our card](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2006-adler-unsupervised-morpheme-based-hmm-hebrew/)
3. C. Cardie and D. Pierce. 1998. Error-driven pruning of treebank grammars for base noun phrase identification. In ACL-1998. [↗](https://doi.org/10.48550/arxiv.cmp-lg/9808015)
4. Y. Goldberg, M. Adler, and M. Elhadad. 2006. Noun phrase chunking in hebrew: Influence of lexical and morphological features. In COLING/ACL2006. [find](https://scholar.google.com/scholar?q=Y%2E+Goldberg%2C+M%2E+Adler%2C+and+M%2E+Elhadad%2E+2006%2E+Noun+phrase+chunking+in+hebrew%3A+Influence+of+lexical+and+morphological+features%2E+In+COLING%2FACL2006%2E) [our card](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2006-goldberg-noun-phrase-chunking-hebrew-influence/)
5. T. Kudo and Y. Matsumoto. 2000. Use of support vector learning for chunk identification. In CoNLL-2000. [find](https://scholar.google.com/scholar?q=T%2E+Kudo+and+Y%2E+Matsumoto%2E+2000%2E+Use+of+support+vector+learning+for+chunk+identification%2E+In+CoNLL%2D2000%2E)
6. T. Kudo and Y. Matsumoto. 2003. Fast methods for kernel-based text analysis. In ACL-2003. [find](https://scholar.google.com/scholar?q=T%2E+Kudo+and+Y%2E+Matsumoto%2E+2003%2E+Fast+methods+for+kernel%2Dbased+text+analysis%2E+In+ACL%2D2003%2E)
7. M. Marcus and L. Ramshaw. 1995. Text Chunking Using Transformation-Based Learning. In Proc. of the 3rd ACL Workshop on Very Large Corpora. [find](https://scholar.google.com/scholar?q=M%2E+Marcus+and+L%2E+Ramshaw%2E+1995%2E+Text+Chunking+Using+Transformation%2DBased+Learning%2E+In+Proc%2E+of+the+3rd+ACL+Workshop+on+Very+Large+Corpora%2E)
8. T. Nakagawa and Y. Matsumoto. 2002. Detecting errors in corpora using support vector machines. In COLING-2002. [find](https://scholar.google.com/scholar?q=T%2E+Nakagawa+and+Y%2E+Matsumoto%2E+2002%2E+Detecting+errors+in+corpora+using+support+vector+machines%2E+In+COLING%2D2002%2E)
9. Erik F. Tjong Kim Sang and S. Buchholz. 2000. Introduction to the conll-2000 shared task: chunking. In CoNLL-2000. [find](https://scholar.google.com/scholar?q=Erik+F%2E+Tjong+Kim+Sang+and+S%2E+Buchholz%2E+2000%2E+Introduction+to+the+conll%2D2000+shared+task%3A+chunking%2E+In+CoNLL%2D2000%2E)
10. K. Sima’an, A. Itai, Y. Winter, A. Altman, and N. Nativ. 2001. Building a tree-bank of modern hebrew text. Traitement Automatique des Langues, 42(2). [find](https://scholar.google.com/scholar?q=K%2E+Sima%E2%80%99an%2C+A%2E+Itai%2C+Y%2E+Winter%2C+A%2E+Altman%2C+and+N%2E+Nativ%2E+2001%2E+Building+a+tree%2Dbank+of+modern+hebrew+text%2E+Traitement+Automatique+des+Langues%2C+42%282%29%2E)
11. V. Vapnik. 1995. The nature of statistical learning theory. Springer-Verlag New York, Inc. [↗](https://doi.org/10.1007/978-1-4757-2440-0)