--- title: "Corpus Based PP Attachment Ambiguity Resolution with a Semantic Dictionary — Stetina 1997" description: "The authors replace string matching with a semantic distance measure over WordNet. 88.1% accuracy. 3 references, cited by 36 papers here." authors: ["Jiri Stetina", "Makoto Nagao"] year: 1997 venue: "Fifth Workshop on Very Large Corpora" source: "https://aclanthology.org/W97-0109/" 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/stetina-1997-corpus-based-pp-attachment-ambiguity/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/stetina-1997-corpus-based-pp-attachment-ambiguity/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [1997](https://md.research.elamur.ai/free/en/papers/1997/) / Corpus Based PP Attachment Ambiguity Resolution with a Semantic Dictionary # Corpus Based PP Attachment Ambiguity Resolution with a Semantic Dictionary **Authors:** Jiri Stetina and Makoto Nagao · **Year:** 1997 · **Venue:** Fifth Workshop on Very Large Corpora · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/) **Links:** [Publisher's page](https://aclanthology.org/W97-0109/) · [PDF](https://aclanthology.org/W97-0109.pdf) · [OpenAlex](https://openalex.org/W1591380337) **Citations:** 79 citations (OpenAlex, 2026-10-14) · [36](https://md.research.elamur.ai/free/en/papers/stetina-1997-corpus-based-pp-attachment-ambiguity/cited-by/) in our library, of the 140,884 papers whose bibliographies we read ## Summary The paper addresses prepositional phrase (PP) attachment: deciding whether a PP modifies the verb or the object noun in verb–noun–preposition–noun quadruples. Earlier corpus methods, such as the Collins and Brooks backed-off model, rely on exact word matches and therefore suffer from sparse data. The authors replace string matching with a semantic distance measure over WordNet. This distance combines path length to the nearest common ancestor with concept depth. Because no large sense-tagged parsed corpus was available, they first annotate the training quadruples from the parsed corpus [MA93] with WordNet senses. They do this with an unsupervised, context-similarity word sense disambiguation procedure. A decision tree is then induced over the sense hierarchy to classify attachments. Its leaves also yield a certainty score. The system reaches about 88.1% accuracy, which is roughly equal to human performance when people see only the quadruple. This suggests that lexical-semantic generalisation can substantially offset missing world knowledge in syntactic disambiguation. ## Key points - **Reference points:** - Using each preposition's most frequent attachment gives a 72.7% baseline. - Humans reach 88.2% on bare quadruples and 93.2% with full sentence context. - The previous best, the Collins and Brooks backed-off model, scored 84.5%. - **Semantic distance:** the measure averages the ratios of path length to depth for both concepts in WordNet. - Identical concepts score 0. - Concepts with no shared ancestor score 1. - **Decision tree:** expansion stops once more than 77% of a node's examples share one class. Errors tend to cluster in low-certainty decisions. - **Results:** overall accuracy is 88.1% on about 3,100 test quadruples. Per-preposition learning curves are unstable below about 1,000 training examples and then plateau at different levels. - **Future work:** the authors expect further gains from wider sentential context, more training data, and more accurate sense tagging. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [AI & machine learning](https://md.research.elamur.ai/free/en/shelves/ai/) ## Cite Cite as: Jiri Stetina and Makoto Nagao. 1997. Corpus Based PP Attachment Ambiguity Resolution with a Semantic Dictionary. Fifth Workshop on Very Large Corpora. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{stetina1997corpus, title = {{Corpus Based PP Attachment Ambiguity Resolution with a Semantic Dictionary}}, author = {Jiri Stetina and Makoto Nagao}, booktitle = {Fifth Workshop on Very Large Corpora}, year = {1997}, url = {https://aclanthology.org/W97-0109/} } ``` - [← previous Resolving bridging references in unrestricted text](https://md.research.elamur.ai/free/en/papers/poesio-1997-resolving-bridging-references-unrestricted-text/) - [next → A Frame-Semantic Approach to Semantic Annotation](https://md.research.elamur.ai/free/en/papers/lowe-1997-frame-semantic-approach-semantic-annotation/) - [↑ back to papers of 1997](https://md.research.elamur.ai/free/en/papers/1997/) ## References 3 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. [a&s88] Altmann, G., Steedman, M., Interaction with Context During Human Sentence Processing. Cognition, 30:191-238,1988. Basili, R., et al, Combining NLP and statistical techniques for lexical acquisition, [B91] [find](https://scholar.google.com/scholar?q=%5Ba%26s88%5D+Altmann%2C+G%2E%2C+Steedman%2C+M%2E%2C+Interaction+with+Context+During+Human+Sentence+Processing%2E+Cognition%2C+30%3A191%2D238%2C1988%2E+Basili%2C+R%2E%2C+et+al%2C+Combining+NLP+and+statistical+techniques+for+lexical+acquis) 2. In Proceedings of the AAAI Fall Symposium on Probabilistic Apporaches to Natural Language, Computational Linguistics, 18(4): 467-480, 1992. [find](https://scholar.google.com/scholar?q=In+Proceedings+of+the+AAAI+Fall+Symposium+on+Probabilistic+Apporaches+to+Natural+Language%2C+Computational+Linguistics%2C+18%284%29%3A+467%2D480%2C+1992%2E) 3. [B&R94] Bfill, E., Resnik, P., A Rule Based Approach to PP Attachment Disambiguation, In Proceedings of COLING, 1994. [find](https://scholar.google.com/scholar?q=%5BB%26R94%5D+Bfill%2C+E%2E%2C+Resnik%2C+P%2E%2C+A+Rule+Based+Approach+to+PP+Attachment+Disambiguation%2C+In+Proceedings+of+COLING%2C+1994%2E)