[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/lex-2014-demelo-etymological-wordnet/)

[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/) / [English](https://md.mova.elamur.ai/free/en/docs/papers/en/) / Etymological Wordnet: Tracing The History of Words

# Etymological Wordnet: Tracing The History of Words

**Authors:** Gerard de Melo · **Year:** 2014 · **Venue:** Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2014) **Link:** [aclanthology.org/L14-1063](https://aclanthology.org/L14-1063/) · **Licence:** [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) (ELRA, LREC 2014 proceedings) — summary only

[**31** citations](https://openalex.org/works?filter=cites:W2250959792) openalex · 2026-10-19[**25** citations in our library](https://md.mova.elamur.ai/free/en/docs/papers/cited-by/lex-2014-demelo-etymological-wordnet/) of the 140673 papers whose bibliographies we read[LREC 2014 (Reykjavik)](https://openalex.org/S7407088301)[licence](https://creativecommons.org/licenses/by-nc-sa/3.0/)

- [Publisher's page](https://doi.org/10.63317/4jkk99tny5y8)
- [PDF](https://aclanthology.org/L14-1063.pdf)
- [DOI 10.63317/4jkk99tny5y8](https://doi.org/10.63317/4jkk99tny5y8)
- [OpenAlex](https://openalex.org/W2250959792)

**Authors (1)**

1. [Gerard de Melo](https://openalex.org/A5085818578) [ORCID](https://orcid.org/0000-0002-2930-2059) · [Semantic Scholar](https://www.semanticscholar.org/author/144608002) · h 41 · 9113 citations · 320 works

Citations and author metrics from openalex (2026-10-19); authors with the same name are not always told apart.

## What it is about

De Melo builds the Etymological Wordnet, a machine-readable network of word origins mined from Wiktionary. Much etymology on Wiktionary is written as prose, so the author uses custom pattern matching over the XML dump, plus the Appendices, gloss references and related-forms sections. The network has over 500,000 word-origin links and over 2 million derivational or compositional links across many languages. The author reports that the precision is roughly 100% against Wiktionary as the ground truth, and the resource mixes origin links with synchronic word-formation links and etymological relatedness links. The paper has no separate evaluation of recall or of the NLP use of the network.

## Ideas

- I1. `en/src/morph.rs`: for archaic forms (hast, doth, -eth, -est), use the origin of the candidate lemma (Germanic, Latin, French, Greek) as a tie-break when two lemmas fit. Measure the lemma accuracy on the archaic tales in `tools/gutenberg` against the current `archaic` mapping.
- I2. `en/src/dict.rs`: store one origin tag per lemma, extracted offline from a raw Wiktionary dump kept in `$MOVA_DATA`. Measure how many EWT and lesson-word lemmas get a tag, and check the two runs are identical.
- I3. Compound check: for words that the morphology splits (for example bio plus logy), test the paper's compound-link idea by comparing the split of `en/src/morph.rs` with the compound link of the same word in the raw dump. Report agreement on a list of 200 compounds.

## For Mova

The touch points are `en/src/morph.rs` (lemma from form, the `archaic` function), `en/src/dict.rs` and `data/lemmas.tsv`. The chapters are [09. Early Modern and archaic forms](https://md.mova.elamur.ai/free/en/docs/languages/en/09-early-modern-and-archaic/) and [16. Derivation I: prefixes](https://md.mova.elamur.ai/free/en/docs/languages/en/16-derivation-prefixes/) with `17-derivation-suffixes.md`. The paper's own data is CC BY-NC-SA, so only the method is used and no such data enters the build. Measure first the lemma accuracy on the archaic tales with and without the origin tie-break.

## Cite

The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.63317/4jkk99tny5y8](https://doi.org/10.63317/4jkk99tny5y8)

```
@inproceedings{melo2014etymological,
  title = {{Etymological Wordnet: Tracing The History of Words}},
  author = {Melo, Gerard de},
  booktitle = {LREC 2014 (Reykjavik)},
  year = {2014},
  doi = {10.63317/4jkk99tny5y8},
  url = {https://doi.org/10.63317/4jkk99tny5y8}
}
```

- [← previous Semi-supervised learning of morphological paradigms and lexicons](https://md.mova.elamur.ai/free/en/docs/papers/lex-2014-ahlberg-paradigm-extraction/)
- [next → WordNet—Wikipedia—Wiktionary: Construction of a Three-way Alignment](https://md.mova.elamur.ai/free/en/docs/papers/lex-2014-miller-wordnet-wikipedia-wiktionary/)
- [↑ back to English](https://md.mova.elamur.ai/free/en/docs/papers/en/)

## References

11 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Burnard, L. and Bauman, S., (2009). TEI P5: Guidelines for Electronic Text Encoding and Interchange, Version 1.4.1. [find](https://scholar.google.com/scholar?q=Burnard%2C+L%2E+and+Bauman%2C+S%2E%2C+%282009%29%2E+TEI+P5%3A+Guidelines+for+Electronic+Text+Encoding+and+Interchange%2C+Version+1%2E4%2E1%2E)
2. TEI Consortium. de Melo, G. and Weikum, G. (2008). Language as a foundation of the Semantic Web. In Bizer, C. and Joshi, A., editors, Proceedings of the Poster and Demonstration Session at the 7th International Semantic Web Conference (ISWC 2008), volume 401 of CEUR WS, Karlsruhe, Germany. [find](https://scholar.google.com/scholar?q=TEI+Consortium%2E+de+Melo%2C+G%2E+and+Weikum%2C+G%2E+%282008%29%2E+Language+as+a+foundation+of+the+Semantic+Web%2E+In+Bizer%2C+C%2E+and+Joshi%2C+A%2E%2C+editors%2C+Proceedings+of+the+Poster+and+Demonstration+Session+at+the+7th+Int)
3. CEUR. de Melo, G. and Weikum, G. (2009). Towards a universal wordnet by learning from combined evidence. In Proc. 18th ACM Conference on Information and Knowledge Management (CIKM 2009). [find](https://scholar.google.com/scholar?q=CEUR%2E+de+Melo%2C+G%2E+and+Weikum%2C+G%2E+%282009%29%2E+Towards+a+universal+wordnet+by+learning+from+combined+evidence%2E+In+Proc%2E+18th+ACM+Conference+on+Information+and+Knowledge+Management+%28CIKM+2009%29%2E)
4. ACM. de Melo, G. and Weikum, G. (2010). Towards universal multilingual knowledge bases. In Bhattacharyya, P., Fellbaum, C., and Vossen, P., editors, Principles, Construction, and Applications of Multilingual Wordnets. Proceedings of the 5th Global WordNet Conference (GWC 2010), pages 149–156, New De… [find](https://scholar.google.com/scholar?q=ACM%2E+de+Melo%2C+G%2E+and+Weikum%2C+G%2E+%282010%29%2E+Towards+universal+multilingual+knowledge+bases%2E+In+Bhattacharyya%2C+P%2E%2C+Fellbaum%2C+C%2E%2C+and+Vossen%2C+P%2E%2C+editors%2C+Principles%2C+Construction%2C+and+Applications+of+Multi)
5. Narosa Publishing. de Melo, G. and Weikum, G. (2012). UWN: A large multilingual lexical knowledge base. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, pages 151–156, Stroudsburg, PA, USA. Association for Computational Linguistics. de Melo, G. (2014). Lexv… [find](https://scholar.google.com/scholar?q=Narosa+Publishing%2E+de+Melo%2C+G%2E+and+Weikum%2C+G%2E+%282012%29%2E+UWN%3A+A+large+multilingual+lexical+knowledge+base%2E+In+Proceedings+of+the+50th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+page)
6. Haspelmath, M. and Tadmor, U., editors. (2009). WOLD. Max Planck Institute for Evolutionary Anthropology, Leipzig. [find](https://scholar.google.com/scholar?q=Haspelmath%2C+M%2E+and+Tadmor%2C+U%2E%2C+editors%2E+%282009%29%2E+WOLD%2E+Max+Planck+Institute+for+Evolutionary+Anthropology%2C+Leipzig%2E)
7. Hoad, T. F. (1993). The Concise Oxford dictionary of English etymology. Oxford University Press Oxford. [find](https://scholar.google.com/scholar?q=Hoad%2C+T%2E+F%2E+%281993%29%2E+The+Concise+Oxford+dictionary+of+English+etymology%2E+Oxford+University+Press+Oxford%2E)
8. Nastase, V. and Strapparava, C. (2013). Bridging languages through etymology: The case of cross language text categorization. In Proceedings of ACL 2013. [find](https://scholar.google.com/scholar?q=Nastase%2C+V%2E+and+Strapparava%2C+C%2E+%282013%29%2E+Bridging+languages+through+etymology%3A+The+case+of+cross+language+text+categorization%2E+In+Proceedings+of+ACL+2013%2E)
9. Seifart, F., editor. (2013). AfBo: A world-wide survey of affix borrowing. Max Planck Institute for Evolutionary Anthropology, Leipzig. [find](https://scholar.google.com/scholar?q=Seifart%2C+F%2E%2C+editor%2E+%282013%29%2E+AfBo%3A+A+world%2Dwide+survey+of+affix+borrowing%2E+Max+Planck+Institute+for+Evolutionary+Anthropology%2C+Leipzig%2E)
10. Swadesh, M., Sherzer, J., and Hymes, D. (1971). The Origin and Diversification of Language. Routledge and K. Paul. [find](https://scholar.google.com/scholar?q=Swadesh%2C+M%2E%2C+Sherzer%2C+J%2E%2C+and+Hymes%2C+D%2E+%281971%29%2E+The+Origin+and+Diversification+of+Language%2E+Routledge+and+K%2E+Paul%2E)
11. Sweetser, E. (1990). From Etymology to Pragmatics: Metaphorical and Cultural Aspects of Semantic Structure. Number v. 54 in Cambridge Studies in Linguistics. Cambridge University Press. [find](https://scholar.google.com/scholar?q=Sweetser%2C+E%2E+%281990%29%2E+From+Etymology+to+Pragmatics%3A+Metaphorical+and+Cultural+Aspects+of+Semantic+Structure%2E+Number+v%2E+54+in+Cambridge+Studies+in+Linguistics%2E+Cambridge+University+Press%2E)