---
title: "Part-of-Speech Tagging for Middle English through Alignment and Projection of Parallel — Moon 2007"
description: "The paper builds a Middle English tagger without hand-tagged data. 84.8% accuracy. 19 references, cited by 11 papers here."
authors: ["Taesun Moon", "Jason Baldridge"]
year: 2007
venue: "Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)"
source: "https://aclanthology.org/D07-1041/"
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/moon-2007-part-speech-tagging-middle-english/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/moon-2007-part-speech-tagging-middle-english/)

[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/) / Part-of-Speech Tagging for Middle English through Alignment and Projection of Parallel Diachronic Texts

# Part-of-Speech Tagging for Middle English through Alignment and Projection of Parallel Diachronic Texts

**Authors:** Taesun Moon and [Jason Baldridge](https://md.research.elamur.ai/free/en/authors/jason-baldridge/) · **Year:** 2007 · **Venue:** Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL) **Link:** [aclanthology.org/D07-1041](https://aclanthology.org/D07-1041/) · **Licence:** [CC BY-NC-SA 3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/) — summary only

[**21** citations](https://openalex.org/works?filter=cites:W70524345) OpenAlex, 2026-10-14 · [**11** citations in our library](https://md.research.elamur.ai/free/en/papers/moon-2007-part-speech-tagging-middle-english/cited-by/) of the 140,884 papers whose bibliographies we read · [Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)](https://aclanthology.org/volumes/D07-1/) · [licence](https://creativecommons.org/licenses/by-nc-sa/3.0/)

- [Publisher's page](https://aclanthology.org/D07-1041/)
- [PDF](https://aclanthology.org/D07-1041.pdf)
- [OpenAlex](https://openalex.org/W70524345)

**Authors (2)**

1. [Taesun Moon](https://openalex.org/A5004719091) [Semantic Scholar](https://www.semanticscholar.org/author/47858323) · h 9 · 214 citations · 21 works
2. [Jason Baldridge](https://openalex.org/A5048931310) [ORCID](https://orcid.org/0000-0002-4712-1841) · [Semantic Scholar](https://www.semanticscholar.org/author/1387994164) · h 45 · 7,433 citations · 135 works

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

## What it is about

The paper builds a Middle English tagger without hand-tagged data. Modern English text is tagged by a maximum-entropy tagger trained on the Wall Street Journal. The tags are projected to Middle English Wycliffe Bible text through word alignments of parallel verses. A bigram tagger cleans the projected tags, and a second maximum-entropy tagger is trained on the WSJ text and the cleaned Middle English text. On Biblical test text it reaches 84.8% accuracy for coarse tags, against a baseline of 63.4%. Other Middle English texts stay in the 60s. About 600 hand-labelled sentences were needed to match the best bootstrapped line.

## Ideas

- I3. Learning curve as a planning tool: plot tagging accuracy against the number of hand-labelled sentences, as the paper does, before adding a new historical book to tools/gutenberg. Run it first on the EWT dev section to test the method.

## For Mova

- I1. `en/src/ptag.rs` and `tools/treeagree`: project tags from `en` onto a verse-aligned parallel text (for example, a translation of a tools/gutenberg lesson), then train the perceptron on the projected tags. Measure accuracy on held-out lessons against the baseline of the current tagger.
- I2. Noise filter: keep only projected tags where the alignment and a bigram check agree, as the paper's cleanup does. Decide by `en folds`, not by one run.

The chapters are [languages/en/09-early-modern-and-archaic.md](https://mova.elamur.ai/free/en/docs/languages/en/09-early-modern-and-archaic/) and [languages/en/10-word-classes.md](https://mova.elamur.ai/free/en/docs/languages/en/10-word-classes/). The code is `en/src/ptag.rs` and `tools/treeagree`. The PPCME data is NC: use it only for tests. Measure first how many tokens of a verse-aligned lesson keep the same tag after projection.

## Institutions

[🎓**The University of Texas at Austin** Austin · United States 51 works · 52,106 citations](https://md.research.elamur.ai/free/en/universities/the-university-of-texas-at-austin/)

Topics[Part-of-speech tagging](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/) · [Historical linguistics & language change](https://md.research.elamur.ai/free/en/topics/language-change/)

## Cite

Cite as Taesun Moon and Jason Baldridge. 2007. Part-of-Speech Tagging for Middle English through Alignment and Projection of Parallel Diachronic Texts. Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL).

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

```bibtex
@inproceedings{moon2007part,
  title = {{Part-of-Speech Tagging for Middle English through Alignment and Projection of Parallel Diachronic Texts}},
  author = {Taesun Moon and Jason Baldridge},
  booktitle = {Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)},
  year = {2007},
  url = {https://aclanthology.org/D07-1041/}
}
```

- [← previous Morphological Disambiguation of Hebrew: A Case Study in Classifier Combination](https://md.research.elamur.ai/free/en/papers/shacham-2007-morphological-disambiguation-hebrew-case-study/)
- [next → Token-based Chunking of Turn-internal Dialogue Act Sequences](https://md.research.elamur.ai/free/en/papers/lendvai-2007-token-based-chunking-turn-internal/)
- [↑ back to papers of 2007](https://md.research.elamur.ai/free/en/papers/2007/)

## References

19 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Eric Brill. 1995. Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging. Computational Linguistics, 21(4):543–565. [our card](https://md.research.elamur.ai/free/en/papers/brill-1995-transformation-based-error-driven-learning/)
2. Helena Britto, Marcelo Finger, and Charlotte Galves, 2002. Computational and linguistic aspects of the construction of The Tycho Brahe Parsed Corpus of Historical Portuguese. Tübingen: Narr. [find](https://scholar.google.com/scholar?q=Helena+Britto%2C+Marcelo+Finger%2C+and+Charlotte+Galves%2C+2002%2E+Computational+and+linguistic+aspects+of+the+construction+of+The+Tycho+Brahe+Parsed+Corpus+of+Historical+Portuguese%2E+Tu%CC%88bingen%3A+Narr%2E)
3. Peter A. Chew, Steve J. Verzi, Travis L. Bauer, and Jonathan T. McClain. 2006. Evaluation of the bible as a resource for cross-language information retrieval. In Proceedings of the Workshop on Multilingual Language Resources and Interoperability, Sydney, July 2006, pages 68–74. [find](https://scholar.google.com/scholar?q=Peter+A%2E+Chew%2C+Steve+J%2E+Verzi%2C+Travis+L%2E+Bauer%2C+and+Jonathan+T%2E+McClain%2E+2006%2E+Evaluation+of+the+bible+as+a+resource+for+cross%2Dlanguage+information+retrieval%2E+In+Proceedings+of+the+Workshop+on+Multili)
4. James R Curran and Stephen Clark. 2003. Investigating gis and smoothing for maximum entropy taggers. In Proceedings of the 11th Meeting of the European Chapter of the Association for Computational Linguistics (EACL-03). [find](https://scholar.google.com/scholar?q=James+R+Curran+and+Stephen+Clark%2E+2003%2E+Investigating+gis+and+smoothing+for+maximum+entropy+taggers%2E+In+Proceedings+of+the+11th+Meeting+of+the+European+Chapter+of+the+Association+for+Computational+Lin)
5. Lee R. Dice. 1945. Measures of the amount of ecologic association between species. Journal of Ecology, 26:297–302. [find](https://scholar.google.com/scholar?q=Lee+R%2E+Dice%2E+1945%2E+Measures+of+the+amount+of+ecologic+association+between+species%2E+Journal+of+Ecology%2C+26%3A297%E2%80%93302%2E)
6. Elliott Franco Drábek and David Yarowsky. 2005. Induction of fine-grained part-of-speech taggers via classifier combination and crosslingual projection. In Proceedings of the ACL Workshop on Building and Using Parallel Texts, pages 49–56, Ann Arbor, Michigan, June. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Elliott+Franco+Dra%CC%81bek+and+David+Yarowsky%2E+2005%2E+Induction+of+fine%2Dgrained+part%2Dof%2Dspeech+taggers+via+classifier+combination+and+crosslingual+projection%2E+In+Proceedings+of+the+ACL+Workshop+on+Building)
7. Barbara A. Fennell. 2001. A History of English: A Sociolinguistic Approach. Blackwell, Oxford. [find](https://scholar.google.com/scholar?q=Barbara+A%2E+Fennell%2E+2001%2E+A+History+of+English%3A+A+Sociolinguistic+Approach%2E+Blackwell%2C+Oxford%2E)
8. Chung-Hye Han, 2000. The Evolution of Do-Support In English Imperatives, pages 275–295. Oxford University Press. [find](https://scholar.google.com/scholar?q=Chung%2DHye+Han%2C+2000%2E+The+Evolution+of+Do%2DSupport+In+English+Imperatives%2C+pages+275%E2%80%93295%2E+Oxford+University+Press%2E)
9. Martin Kay and Martin Röscheisen. 1993. Text-translation alignment. Computational Linguistics, 19(1):121–142. [our card](https://md.research.elamur.ai/free/en/papers/kay-1993-text-translation-alignment/)
10. Anthony Kroch and Ann Taylor. 2000. Penn-helsinki parsed corpus of middle english, second edition. [find](https://scholar.google.com/scholar?q=Anthony+Kroch+and+Ann+Taylor%2E+2000%2E+Penn%2Dhelsinki+parsed+corpus+of+middle+english%2C+second+edition%2E)
11. Anthony Kroch, Ann Taylor, and Donald Ringe. 2000. The middle english verb-second constraint: A case study in language contact and language change. Amsterdam Studies in the Theory and History of Linguistic Science Series, 4:353–392. [find](https://scholar.google.com/scholar?q=Anthony+Kroch%2C+Ann+Taylor%2C+and+Donald+Ringe%2E+2000%2E+The+middle+english+verb%2Dsecond+constraint%3A+A+case+study+in+language+contact+and+language+change%2E+Amsterdam+Studies+in+the+Theory+and+History+of+Lingu)
12. Mitchell P. Marcus, Beatrice Santorini, and Mary Ann Marcinkiewicz. 1994. Building a large annotated corpus of english: The penn treebank. Computational Linguistics, 19(2):313–330. [our card](https://md.research.elamur.ai/free/en/papers/marcus-1993-building-large-annotated-corpus-english/)
13. Dan I. Melamed. 1998. Manual annotation of translation equivalence: The blinker project. In Technical Report 98-07, Institute for Research in Cognitive Science, Philadelphia. [find](https://scholar.google.com/scholar?q=Dan+I%2E+Melamed%2E+1998%2E+Manual+annotation+of+translation+equivalence%3A+The+blinker+project%2E+In+Technical+Report+98%2D07%2C+Institute+for+Research+in+Cognitive+Science%2C+Philadelphia%2E)
14. Franz Josef Och and Hermann Ney. 2003. A systematic comparison of various statistical alignment models. Computational Linguistics, 29(1):19–51. [find](https://scholar.google.com/scholar?q=Franz+Josef+Och+and+Hermann+Ney%2E+2003%2E+A+systematic+comparison+of+various+statistical+alignment+models%2E+Computational+Linguistics%2C+29%281%29%3A19%E2%80%9351%2E)
15. Sylwia Ozdowska. 2006. Projecting pos tags and syntactic dependencies from english and french to polish in aligned corpora. In EACL 2006 Workshop on Cross-Language Knowledge Induction. [find](https://scholar.google.com/scholar?q=Sylwia+Ozdowska%2E+2006%2E+Projecting+pos+tags+and+syntactic+dependencies+from+english+and+french+to+polish+in+aligned+corpora%2E+In+EACL+2006+Workshop+on+Cross%2DLanguage+Knowledge+Induction%2E)
16. Adwait Ratnaparkhi. 1996. A maximum entropy model for part-of-speech tagging. In Eric Brill and Kenneth Church, editors, Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 133–142. Association for Computational Linguistics, Somerset, New Jersey. [our card](https://md.research.elamur.ai/free/en/papers/ratnaparkhi-1996-maximum-entropy-model-part-speech/)
17. Philip Resnik, Mari Broman Olsen, and Mona Diab. 1999. The bible as a parallel corpus: Annotating the ”book of 2000 tongues”. Computers and the Humanities, 33(1–2):129–153. [find](https://scholar.google.com/scholar?q=Philip+Resnik%2C+Mari+Broman+Olsen%2C+and+Mona+Diab%2E+1999%2E+The+bible+as+a+parallel+corpus%3A+Annotating+the+%E2%80%9Dbook+of+2000+tongues%E2%80%9D%2E+Computers+and+the+Humanities%2C+33%281%E2%80%932%29%3A129%E2%80%93153%2E)
18. David Yarowsky and Grace Ngai. 2001. Inducing multilingual pos taggers and np bracketers via robust projection across aligned corpora. In NAACL ’01: Second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies 2001, pages 1–8, Morristown, NJ, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=David+Yarowsky+and+Grace+Ngai%2E+2001%2E+Inducing+multilingual+pos+taggers+and+np+bracketers+via+robust+projection+across+aligned+corpora%2E+In+NAACL+%E2%80%9901%3A+Second+meeting+of+the+North+American+Chapter+of+the)
19. David Yarowsky, Grace Ngai, and Richard Wicentowski. 2001. Inducing multilingual text analysis tools via robust projection across aligned corpora. In HLT ’01: Proceedings of the first international conference on Human language technology research, pages 1–8, Morristown, NJ, USA. Association for Computational Linguistics. [our card](https://md.research.elamur.ai/free/en/papers/yarowsky-2001-inducing-multilingual-text-analysis-tools/)