--- title: "PP Attachment: Where do We Stand? — Kok 2017" description: "Prepositional phrase (PP) attachment is one of the most frequent parser errors: in the authors' German parser about 18% of labelled attachment errors are…" authors: ["Daniël de Kok", "Jianqiang Ma", "Corina Dima", "Erhard Hinrichs"] year: 2017 venue: "Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers" source: "https://aclanthology.org/E17-2050/" doi: "10.18653/v1/e17-2050" 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/onto-2017-kok-pp-attachment-where-do-we/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/onto-2017-kok-pp-attachment-where-do-we/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/page/3/) / PP Attachment: Where do We Stand? # PP Attachment: Where do We Stand? **Authors:** Daniël de Kok, Jianqiang Ma, Corina Dima, [Erhard Hinrichs](https://md.research.elamur.ai/free/en/authors/erhard-hinrichs/) · **Year:** 2017 · **Venue:** Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers **Link:** [aclanthology.org/E17-2050](https://aclanthology.org/E17-2050/) · **Licence:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) [**8** citations](https://openalex.org/works?filter=cites:W2740079198) OpenAlex · 2026-10-14 · [**7** citations in our library](https://md.research.elamur.ai/free/en/papers/onto-2017-kok-pp-attachment-where-do-we/cited-by/) of the 140673 papers whose bibliographies we read · [Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers](https://aclanthology.org/volumes/E17-2/) · [licence](https://creativecommons.org/licenses/by/4.0/) - [Publisher's page](https://aclanthology.org/E17-2050/) - [PDF](https://aclanthology.org/E17-2050.pdf) - [DOI 10.18653/v1/e17-2050](https://doi.org/10.18653/v1/e17-2050) - [OpenAlex](https://openalex.org/W2740079198) **Authors (4)** 1. [Daniël de Kok](https://openalex.org/A5030988529) h 6 · 219 citations · 54 works 2. [Jianqiang Ma](https://openalex.org/A5101523859) [ORCID](https://orcid.org/0009-0009-8814-0609) · h 9 · 529 citations · 39 works 3. [Corina Dima](https://openalex.org/A5065338642) [ORCID](https://orcid.org/0000-0001-7409-4992) · h 6 · 142 citations · 24 works 4. [Erhard Hinrichs](https://openalex.org/A5108637841) h 22 · 2087 citations · 149 works Citations and author metrics: OpenAlex, 2026-10-14; authors with the same name are not always told apart. ## What it is about Prepositional phrase (PP) attachment is one of the most frequent parser errors: in the authors' German parser about 18% of labelled attachment errors are PP attachments. The paper treats attachment as a choice among all candidate heads of a preposition (3.15 on average), scored by a feed-forward network. The inputs are word and tag embeddings, topological-field features from the clause structure, and auxiliary bilexical preference distributions (pointwise mutual information) estimated from a parse of 28.8 million sentences of newspaper text. On a German data set of about 44,000 instances, the accuracy rises from 56.9% for logistic regression to 86.5% with all features and 86.7% with auxiliary counts from unambiguous attachments only. The error analysis puts the ceiling near 92.6%: most remaining errors are ambiguities that the gold standard marks as one of several correct attachments, or that need discourse context. ## Ideas - I1. `en/src/parse.rs`: treat PP attachment as a candidate choice for `obl`, `nmod` and `advcl` arcs with a PP head, and measure the attachment accuracy on EWT test and the share of labelled errors it accounts for (the paper finds 18% in German). - I2. Auxiliary bilexical counts (PMI of preposition-object-head triples) from the school silver corpus (`annot`, 1.17M words) and from the `en` parses of a larger raw collection; metric: accuracy on EWT PP attachments with and without the counts. The data is English, not the German set of the paper. - I3. Ceiling check first: count the EWT PP attachments that have two or more defensible heads, as the paper's ceiling argument does, and report the accuracy ceiling per treebank before tuning any model. ## For Mova The chapter is [languages/en/22-phrases.md](https://mova.elamur.ai/free/en/docs/languages/en/22-phrases/), with `23-complementation.md` for the verb-or-noun choice. The code is `en/src/parse.rs` (the candidate set) and `en/src/ctx.rs` (document context). The German numbers are not Mova's numbers; any English figure must come from EWT test. ## Cite The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.18653/v1/e17-2050](https://doi.org/10.18653/v1/e17-2050) ```bibtex @inproceedings{kok2017pp, title = {{PP Attachment: Where do We Stand?}}, author = {Kok, Daniël de and Ma, Jianqiang and Dima, Corina and Hinrichs, Erhard}, booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers}, year = {2017}, doi = {10.18653/v1/e17-2050}, url = {https://doi.org/10.18653/v1/e17-2050} } ``` - [← previous Poincaré Embeddings for Learning Hierarchical Representations](https://md.research.elamur.ai/free/en/papers/nickel-2017-poincare-embeddings-learning-hierarchical-representations/) - [next → Predictor-Estimator using Multilevel Task Learning with Stack Propagation for Neural Quality Estimation](https://md.research.elamur.ai/free/en/papers/kim-2017-predictor-estimator-multilevel-task-learning/) - [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/page/3/) ## References 1 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Table 2: Error analysis of a random sample of 100 PPs that are incorrectly attached by the best model.* Yonatan Belinkov, Tao Lei, Regina Barzilay, and Amir Globerson. 2014. Exploring compositional architectures and word vector representations for prepositional phrase attachment. Transactions of the Association for Computational Linguistics, 2:561–572. [find](https://scholar.google.com/scholar?q=Table+2%3A+Error+analysis+of+a+random+sample+of+100+PPs+that+are+incorrectly+attached+by+the+best+model%2E%2A+Yonatan+Belinkov%2C+Tao+Lei%2C+Regina+Barzilay%2C+and+Amir+Globerson%2E+2014%2E+Exploring+compositional+ar) [our card](https://md.research.elamur.ai/free/en/papers/tacl-2014-belinkov-exploring-compositional-architectures-word-vector/)