---
title: "Adapting WSJ-Trained Parsers to the British National Corpus Using In-Domain — Foster 2007"
description: "The authors build a gold set of 1,000 BNC sentences (500 for development, 500 for test), chosen to contain verbs… 12 references, cited by 9 papers here."
authors: ["Jennifer Foster", "Joachim Wagner", "Djamé Seddah", "Josef van Genabith"]
year: 2007
venue: "Proceedings of the Tenth International Conference on Parsing Technologies"
source: "https://aclanthology.org/W07-2204/"
doi: "10.3115/1621410.1621414"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/foster-2007-adapting-wsj-trained-parsers-british/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/foster-2007-adapting-wsj-trained-parsers-british/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2007](https://md.research.elamur.ai/free/en/papers/2007/) / Adapting WSJ-Trained Parsers to the British National Corpus Using In-Domain Self-Training

# Adapting WSJ-Trained Parsers to the British National Corpus Using In-Domain Self-Training

**Authors:** [Jennifer Foster](https://md.research.elamur.ai/free/en/authors/jennifer-foster/), [Joachim Wagner](https://md.research.elamur.ai/free/en/authors/joachim-wagner/), [Djamé Seddah](https://md.research.elamur.ai/free/en/authors/djame-seddah/) and [Josef van Genabith](https://md.research.elamur.ai/free/en/authors/josef-van-genabith/) · **Year:** 2007 · **Venue:** Proceedings of the Tenth International Conference on Parsing Technologies (IWPT 2007) **Link:** [aclanthology.org/W07-2204](https://aclanthology.org/W07-2204/) · **Licence:** [CC BY-NC-SA 3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/) — summary only

[**16** citations](https://openalex.org/works?filter=cites:W1965897786) OpenAlex, 2026-10-14 · [**9** citations in our library](https://md.research.elamur.ai/free/en/papers/foster-2007-adapting-wsj-trained-parsers-british/cited-by/) of the 140,884 papers whose bibliographies we read · [Proceedings of the Tenth International Conference on Parsing Technologies](https://aclanthology.org/volumes/W07-22/) · [licence](https://creativecommons.org/licenses/by-nc-sa/3.0/)

- [Publisher's page](https://aclanthology.org/W07-2204/)
- [PDF](https://aclanthology.org/W07-2204.pdf)
- [DOI 10.3115/1621410.1621414](https://doi.org/10.3115/1621410.1621414)
- [OpenAlex](https://openalex.org/W1965897786)

**Authors (4)**

1. [Jennifer Foster](https://openalex.org/A5066497689) [ORCID](https://orcid.org/0000-0002-7789-4853) · [Semantic Scholar](https://www.semanticscholar.org/author/144116340) · h 23 · 2,260 citations · 113 works
2. [Joachim Wagner](https://openalex.org/A5026305513) [ORCID](https://orcid.org/0000-0002-8290-3849) · [Semantic Scholar](https://www.semanticscholar.org/author/145919859) · h 16 · 1,107 citations · 51 works
3. [Djamé Seddah](https://openalex.org/A5010519567) [ORCID](https://orcid.org/0000-0003-0194-8197) · [Semantic Scholar](https://www.semanticscholar.org/author/1679170) · h 22 · 3,411 citations · 203 works
4. [Josef van Genabith](https://openalex.org/A5049194403) [ORCID](https://orcid.org/0000-0003-1322-7944) · [Semantic Scholar](https://www.semanticscholar.org/author/7519068) · h 38 · 5,376 citations · 366 works

Citations and author metrics: OpenAlex, 2026-10-14; authors with the same name are not always told apart.

## What it is about

The question is whether a parser trained on WSJ text can be adapted to another domain without new annotation. The authors build a gold set of 1,000 BNC sentences (500 for development, 500 for test), chosen to contain verbs that do not occur in the WSJ training sections, and parse the whole BNC (6 million sentences, 99.8% parsed) with the Charniak and Johnson reranking parser. They retrain the parser on combinations of its own BNC parses and the WSJ trees, with the WSJ copies repeated. The best mix, one million BNC trees plus WSJ data repeated ten times, raises the BNC test F-score by 1.7 points to 85.6 and the WSJ section 23 F-score to 91.7 (+0.4). The paper concludes that in-domain self-training helps, while the seed domain must keep the original trees.

## For Mova

- I1. Self-training for `en/src/parse.rs`: parse a large raw collection under an open licence with `en`, add those trees to the perceptron training, and repeat the gold EWT training trees 1, 5 or 10 times. Measure LAS on an `en folds` dev fold and on the seed domain, with the silver size varied (50k, 250k, 1000k trees).
- I2. Hard-verb subset: select held-out EWT sentences that contain a verb form unseen in the training trees, as the paper selects its gold sentences, and report LAS on that subset in `en parse-eval`. Measure it before and after I1.
- I3. Lower-bound check: report LAS on the other `treebanks/en/` banks (childes, lines, gum, gentle) before and after I1, so that a gain in one domain cannot hide a loss in the seed domain.

The chapters are [languages/en/37-register-and-variation.md](https://mova.elamur.ai/free/en/docs/languages/en/37-register-and-variation/) and `20-syntax-overview.md`. The code is `en/src/parse.rs` (training), with `en folds`, `en parse-eval` and `treebanks/en/`. The BNC data is NC, so the paper's gold set is test only and never part of what is built. Self-training uses Mova's own trees, so no large model is involved. The large raw run needs the operator's explicit word before it starts.

## Institutions

[🎓**Dublin City University** Dublin · Ireland 48 works · 8,753 citations](https://md.research.elamur.ai/free/en/universities/dublin-city-university/)

## Cite

Cite as Jennifer Foster, Joachim Wagner, Djamé Seddah and Josef van Genabith. 2007. Adapting WSJ-Trained Parsers to the British National Corpus Using In-Domain Self-Training. Proceedings of the Tenth International Conference on Parsing Technologies.

The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.3115/1621410.1621414](https://doi.org/10.3115/1621410.1621414)

```bibtex
@inproceedings{foster2007adapting,
  title = {{Adapting WSJ-Trained Parsers to the British National Corpus Using In-Domain Self-Training}},
  author = {Jennifer Foster, Joachim Wagner, Djamé Seddah and Josef {van Genabith}},
  booktitle = {Proceedings of the Tenth International Conference on Parsing Technologies},
  year = {2007},
  doi = {10.3115/1621410.1621414},
  url = {https://doi.org/10.3115/1621410.1621414}
}
```

- [← previous Capturing Translational Divergences with a Statistical Tree-to-Tree Aligner](https://md.research.elamur.ai/free/en/papers/hearne-2007-capturing-translational-divergences-statistical-tree/)
- [next → High-accuracy Annotation and Parsing of CHILDES Transcripts](https://md.research.elamur.ai/free/en/papers/sagae-2007-high-accuracy-annotation-parsing-childes/)
- [↑ back to papers of 2007](https://md.research.elamur.ai/free/en/papers/2007/)

## References

12 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Michiel Bacchiani, Michael Riley, Brian Roark, and Richard Sproat. 2006. Map adaptation of stochastic grammars. Computer Speech and Language, 20(1):41–68. [find](https://scholar.google.com/scholar?q=Michiel+Bacchiani%2C+Michael+Riley%2C+Brian+Roark%2C+and+Richard+Sproat%2E+2006%2E+Map+adaptation+of+stochastic+grammars%2E+Computer+Speech+and+Language%2C+20%281%29%3A41%E2%80%9368%2E)
2. Ann Bies, Mark Ferguson, Karen Katz, and Robert MacIntyre. 1995. Bracketing guidelines for treebank II style, Penn Treebank project. Technical Report MS-CIS-95-06, University of Pennsylvania. [find](https://scholar.google.com/scholar?q=Ann+Bies%2C+Mark+Ferguson%2C+Karen+Katz%2C+and+Robert+MacIntyre%2E+1995%2E+Bracketing+guidelines+for+treebank+II+style%2C+Penn+Treebank+project%2E+Technical+Report+MS%2DCIS%2D95%2D06%2C+University+of+Pennsylvania%2E)
3. Lou Burnard. 2000. User reference guide for the British National Corpus. Technical report, Oxford University. [find](https://scholar.google.com/scholar?q=Lou+Burnard%2E+2000%2E+User+reference+guide+for+the+British+National+Corpus%2E+Technical+report%2C+Oxford+University%2E)
4. Eugene Charniak and Mark Johnson. 2005. Coarse-to-fine nbest-parsing and maxent discriminative reranking. In Proceedings of ACL-05, pages 173–180, Barcelona. [find](https://scholar.google.com/scholar?q=Eugene+Charniak+and+Mark+Johnson%2E+2005%2E+Coarse%2Dto%2Dfine+nbest%2Dparsing+and+maxent+discriminative+reranking%2E+In+Proceedings+of+ACL%2D05%2C+pages+173%E2%80%93180%2C+Barcelona%2E)
5. Eugene Charniak. 2000. A maximum-entropy-inspired parser. In Proceedings of NAACL-00, pages 132–139, Seattle. [our card](https://md.research.elamur.ai/free/en/papers/charniak-2000-maximum-entropy-inspired-parser/)
6. Michael Collins. 2003. Head-driven statistical models for natural language parsing. Computational Linguistics, 29(4):499–637. [our card](https://md.research.elamur.ai/free/en/papers/collins-2003-head-driven-statistical-models-natural/)
7. W. Nelson Francis and Henry Kučera. 1979. Brown Corpus Manual. Technical report, Brown University, Providence. [find](https://scholar.google.com/scholar?q=W%2E+Nelson+Francis+and+Henry+Kuc%CC%8Cera%2E+1979%2E+Brown+Corpus+Manual%2E+Technical+report%2C+Brown+University%2C+Providence%2E)
8. Daniel Gildea. 2001. Corpus variation and parser performance. In Proceedings of EMNLP-01, pages 167–202, Barcelona. [our card](https://md.research.elamur.ai/free/en/papers/gildea-2001-corpus-variation-parser-performance/)
9. Mitchell P. Marcus, Beatrice Santorini, and Mary Ann Marcinkiewicz. 1993. Building a large annotated corpus of English: the Penn Treebank. Computational Linguistics, 19(2):313–330. [↗](https://doi.org/10.21236/ada273556) [our card](https://md.research.elamur.ai/free/en/papers/marcus-1993-building-large-annotated-corpus-english/)
10. David McClosky, Eugene Charniak, and Mark Johnson. 2006a. Effective self-training for parsing. In Proceedings of HLT-NAACL-06, pages 152–159, New York. [our card](https://md.research.elamur.ai/free/en/papers/mcclosky-2006-effective-self-training-parsing/)
11. David McClosky, Eugene Charniak, and Mark Johnson. 2006b. Reranking and self-training for parser adaptation. In Proceedings of COLING-ACL-06, pages 337–344, Sydney. [our card](https://md.research.elamur.ai/free/en/papers/mcclosky-2006-reranking-self-training-parser-adaptation/)
12. Mark Steedman, Miles Osbourne, Anoop Sarkar, Stephen Clark, Rebecca Hwa, Julia Hockenmaier, Paul Ruhlen, Steven Baker, and Jeremiah Crim. 2003. Boot-strapping statistical parsers from small datasets. In Proceedings of EACL-03, Budapest. [find](https://scholar.google.com/scholar?q=Mark+Steedman%2C+Miles+Osbourne%2C+Anoop+Sarkar%2C+Stephen+Clark%2C+Rebecca+Hwa%2C+Julia+Hockenmaier%2C+Paul+Ruhlen%2C+Steven+Baker%2C+and+Jeremiah+Crim%2E+2003%2E+Boot%2Dstrapping+statistical+parsers+from+small+datasets%2E+)