The Grammar of English Deverbal Compounds and their Meaning

What it is about

The question is whether the way a deverbal noun behaves in its own right predicts how its non-head is read in a noun-noun compound such as "task assignment". Grimshaw's theory says that argument-supporting nominals (ASNs) keep verbal arguments, so the non-head is read as an object (OBJ), while result and simple-event nominals take root-compound readings (NOBJ). The authors annotate compounds from the Annotated Gigaword corpus with OBJ or NOBJ (inter-annotator agreement 81.5% on the agreed relations), then extract seven corpus features for each head: how often the head appears in compounds, the share of singular uses outside compounds, the share of "of"-phrases, the suffix, and others. A logistic regression on these features reaches 66.7% accuracy against a 50% random baseline on heads held out from training. The most predictive features are the share of compound use of the head and the share of singular uses with an "of"-phrase, which supports the ASN account and argues against Borer (2013).

Ideas

• I1. Count-based predictor for prag/src/roles.rs: for a noun-noun compound whose head is a deverbal noun, decide OBJ or NOBJ by a decision list over two head counts (compound share, and the share of "of"-phrases outside compounds), with the rule that fired written into the explanation. Measure accuracy on a held-out set against the 50% baseline.
• I2. Head-level, not compound-level, features: store the counts per head in a BTreeMap so that the rule is deterministic and the same head always gets the same decision. Report the ablation for each count (the paper's Table 4 design).
• I3. Use the paper's error class: label tagger errors ("face abandonment" read as a verb) as ERROR and exclude them from the score, so that the POS tagger's failures are not counted as wrong readings.
• I4. Negative control: shuffle the OBJ/NOBJ labels across compounds and check that the decision list falls to chance; and report the random baseline next to every accuracy.

For Mova

The chapters are 18. Compounding, conversion and the minor processes (compounds and conversion) and 16. Derivation I: prefixes and 17. Derivation II: suffixes (deverbal -ing, -er, -ee). The code is prag/src/roles.rs (role reading) and en/src/morph.rs (suffix class). Measures: accuracy on a held-out head split against the 50% baseline, the ablation of each count, and the shuffled-label control, run twice. The paper is CC BY, so its data can be quoted and tested on, but the corpus counts must come from Mova's own open text.

Cite

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

@inproceedings{iordachioaia2016grammar,
  title = {{The Grammar of English Deverbal Compounds and their Meaning}},
  author = {Iordăchioaia, Gianina and Plas, Lonneke van der and Jagfeld, Glorianna},
  booktitle = {Proceedings of the Workshop on Grammar and Lexicon: interactions and interfaces (GramLex)},
  year = {2016},
  url = {https://aclanthology.org/W16-3811/}
}

References

21 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Peter Ackema and Ad Neeleman. 2004. Beyond Morphology. Oxford University Press, Oxford. find
2. Artemis Alexiadou and Jane Grimshaw. 2008. Verbs, nouns, and affixation. In Florian Schäfer, editor, Working Papers of the SFB 732 Incremental Specification in Context, volume 1, pages 1–16. Universität Stuttgart. find
3. Hagit Borer. 2013. Taking Form. Oxford University Press, Oxford. find
4. Noam Chomsky. 1970. Remarks on nominalization. In Roderick A. Jacobs and Peter S. Rosenbaum, editors, Readings in English transformational grammar, pages 184–221. Waltham, MA: Ginn. find
5. Thomas G Dietterich. 1998. Approximate statistical tests for comparing supervised classification learning algorithms. Neural computation, 10(7):1895–1923. ↗
6. Antske Sibelle Fokkens. 2007. A hybrid approach to compound noun disambiguation. MA-thesis. Universität des Saarladens, Saarbrücken. find
7. Dan Gillick. 2009. Sentence boundary detection and the problem with the u.s. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers, NAACL-Short ’09, pages 241–244, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
8. Jane Grimshaw. 1990. Argument Structure. MIT Press, Cambridge, MA. find
9. Claire Grover, Mirella Lapata, and Alex Lascarides. 2005. A comparison of parsing technologies for the biomedical domain. Journal of Natural Language Engineering, 11:01:27–65. ↗
10. Mark Hall, Eibe Frank, Geoffrey Holmes, Bernhard Pfahringer, Peter Reutemann, and Ian H. Witten. 2009. The weka data mining software: An update. SIGKDD Explorations, 11(1):10–18. ↗
11. Zhongqiang Huang, Mary Harper, and Slav Petrov. 2010. Self-training with products of latent variable grammars. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, EMNLP ’10, pages 12–22, Stroudsburg, PA, USA. Association for Computational Linguistics. find
12. Angelika Kratzer. 1996. Severing the external argument from its verb. In Johan Rooryck and Laurie Zaring, editors, Phrase Structure and the Lexicon, pages 109–137. Kluwer Academic Publishers. ↗
13. Mirella Lapata. 2002. The disambiguation of nominalizations. Journal of Computational Linguistics, 28:3:357– 388. ↗
14. Judith N. Levi. 1978. The Syntax and Semantics of Complex Nominals. Academic Press, New York. find
15. Rochelle Lieber. 2004. Morphology and Lexical Semantics. Cambridge University Press, Cambridge. find
16. Courtney Napoles, Matthew Gormley, and Benjamin Van Durme. 2012. Annotated gigaword. In Proceedings of the Joint Workshop on Automatic Knowledge Base Construction and Web-scale Knowledge Extraction, AKBC-WEKEX ’12, pages 95–100, Stroudsburg, PA, USA. Association for Computational Linguistics. find
17. Jeremy Nicholson and Timothy Baldwin. 2006. Interpretation of compound nominalisations using corpus and web statistics. In Proceedings of the Workshop on Multiword Expressions: Identifying and Exploiting Underlying Properties, pages 54–61, Sydney, Australia. find
18. Susan Olsen. 2015. Composition. In Peter O. Müller et al., editors, Word-Formation: An International Handbook of the Languages of Europe, volume I, pages 364–386. De Gruyter. find
19. Thomas Roeper and Muffy Siegel. 1978. A lexical transformation for verbal compounds. Linguistic Inquiry, 9:199–260. find
20. Ina Rösiger, Johannes Schäfer, Tanja George, Simon Tannert, Ulrich Heid, and Michael Dorna. 2015. Extracting terms and their relations from german texts: Nlp tools for the preparation of raw material for e-dictionaries. In Proceedings of eLex 2015, pages 486–503. Herstmonceux Castle, UK. find
21. Elisabeth O. Selkirk. 1982. The Syntax of Words. MIT Press, Cambridge, MA. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/chioaia-2016-grammar-english-deverbal-compounds-their/