--- title: "The Role of Modifier and Head Properties in — Walde 2016" description: "The paper asks which properties of a noun-noun compound's modifier and head make its degree of compositionality easier to predict from a vector space. It…" authors: ["Sabine Schulte im Walde", "Anna Hätty", "Stefan Bott"] year: 2016 venue: "Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics" source: "https://aclanthology.org/S16-2020/" doi: "10.18653/v1/s16-2020" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/walde-2016-role-modifier-head-properties-predicting/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/walde-2016-role-modifier-head-properties-predicting/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2016](https://md.research.elamur.ai/free/en/papers/2016/page/3/) / The Role of Modifier and Head Properties in Predicting the Compositionality of English and German Noun-Noun Compounds: A Vector-Space Perspective # The Role of Modifier and Head Properties in Predicting the Compositionality of English and German Noun-Noun Compounds: A Vector-Space Perspective **Authors:** [Sabine Schulte im Walde](https://md.research.elamur.ai/free/en/authors/sabine-schulte-im-walde/), Anna Hätty, Stefan Bott · **Year:** 2016 · **Venue:** Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics (*SEM 2016) **Link:** [aclanthology.org/S16-2020](https://aclanthology.org/S16-2020/) · **Licence:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) (ACL Anthology) [**13** citations](https://openalex.org/works?filter=cites:W2515351962) OpenAlex · 2026-10-14 · [**15** citations in our library](https://md.research.elamur.ai/free/en/papers/walde-2016-role-modifier-head-properties-predicting/cited-by/) of the 140673 papers whose bibliographies we read · [Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics](https://aclanthology.org/volumes/S16-2/) · [licence](https://creativecommons.org/licenses/by/4.0/) - [Publisher's page](https://aclanthology.org/S16-2020/) - [PDF](https://aclanthology.org/S16-2020.pdf) - [DOI 10.18653/v1/s16-2020](https://doi.org/10.18653/v1/s16-2020) - [OpenAlex](https://openalex.org/W2515351962) **Authors (3)** 1. [Sabine Schulte im Walde](https://openalex.org/A5036567696) [ORCID](https://orcid.org/0000-0002-8975-6255) · [Semantic Scholar](https://www.semanticscholar.org/author/2284872754) · h 29 · 2783 citations · 189 works 2. [Anna Hätty](https://openalex.org/A5067024917) [ORCID](https://orcid.org/0009-0002-0085-6784) · [Semantic Scholar](https://www.semanticscholar.org/author/3449046) · h 8 · 217 citations · 26 works 3. [Stefan Bott](https://openalex.org/A5051720921) [ORCID](https://orcid.org/0009-0002-7365-9482) · [Semantic Scholar](https://www.semanticscholar.org/author/2736946) · h 14 · 701 citations · 61 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 asks which properties of a noun-noun compound's modifier and head make its degree of compositionality easier to predict from a vector space. It uses co-occurrence vectors (sentence-internal window of 20 words each side, local mutual information) from the COW corpora and the cosine between compound and constituent. The new German gold standard, GhoSt-NN, has 180 compounds (balanced) and 868 compounds (extended), rated for compositionality on a 1–6 scale. For English, the compound-head prediction reaches Spearman ρ = 0.60 on the Reddy set (90 compounds), while the both-constituent score on the 1,443-item Ó Séaghdha set is only 0.35. Compounds with low-frequency, low-productivity and low-ambiguity heads are predicted better; the ambiguity effect is significant in the extended GhoSt-NN set (p \< 0.01). Relation types also differ, with BE compounds predicted best and ACTOR compounds worst. ## Ideas - I1. `en/src/dict.rs`: the head's number of senses, from the lexicon, as a gate on the compositional reading. Heads with more than two senses get a "lexicalised" flag. Measure on English compounds with the standard ratings, if a licensed set can be used; control with a random flag. - I2. the dictionary builder: the same ambiguity feature on pupil compounds ("birthday cake", "sunflower"). Check that the compound's sense is chosen from the correct head sense in the school questions. - I3. Relation classes as rules in `prag`: the relation (for example "made of", "for", "about") from prepositional and verbal cues, with per-class accuracy reported. Keep the relation enum deterministic. - I4. A count-based replacement for the vector cosine: pointwise mutual information over corpus counts in `BTreeMap` tables, run twice to confirm identical output. ## For Mova The English chapter is [languages/en/18-compounding-conversion-minor.md](https://mova.elamur.ai/free/en/docs/languages/en/18-compounding-conversion-minor/), and the lexicon is `en/src/dict.rs`. The paper's results are correlations, not a rule, so Mova would need its own gold data. The German data are not for Mova now. The clearest English point is the head-ambiguity effect, which can be measured with the existing sense table. ## Cite The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.18653/v1/s16-2020](https://doi.org/10.18653/v1/s16-2020) ```bibtex @inproceedings{walde2016role, title = {{The Role of Modifier and Head Properties in Predicting the Compositionality of English and German Noun-Noun Compounds: A Vector-Space Perspective}}, author = {Walde, Sabine Schulte im and Hätty, Anna and Bott, Stefan}, booktitle = {Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics}, year = {2016}, doi = {10.18653/v1/s16-2020}, url = {https://doi.org/10.18653/v1/s16-2020} } ``` - [← previous The Role of Context Types and Dimensionality in Learning Word Embeddings](https://md.research.elamur.ai/free/en/papers/melamud-2016-role-context-types-dimensionality-learning/) - [next → The Social Impact of Natural Language Processing](https://md.research.elamur.ai/free/en/papers/hovy-2016-social-impact-natural-language-processing/) - [↑ back to papers of 2016](https://md.research.elamur.ai/free/en/papers/2016/page/3/) ## References 2 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Marco Baroni, Silvia Bernardini, Adriano Ferraresi, and Eros Zanchetta. 2009. The WaCky Wide Web: A Collection of Very Large Linguistically Processed Web-Crawled Corpora. Language Resources and Evaluation, 43(3):209–226. [↗](https://doi.org/10.1007/s10579-009-9081-4) 2. Marco Baroni, Raffaella Bernardi, and Roberto Zamparelli. 2014. Frege in Space: A Program for Compositional Distributional Semantics. Linguistic Issues in Language Technologies, 9(6):5–110. [↗](https://doi.org/10.33011/lilt.v9i.1321)