# Ontology-Aware Token Embeddings for Prepositional Phrase Attachment

arXiv: https://arxiv.org/abs/1705.02925 · HTML: https://mlsanity.com/paper/1705.02925/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2017.

## Built on by (most cited first, 1 of 1)

- [Modeling Event Plausibility with Consistent Conceptual Abstraction](https://mlsanity.com/paper/2104.10247/) (2021)

## Abstract (arXiv)

Type-level word embeddings use the same set of parameters to represent all instances of a word regardless of its context, ignoring the inherent lexical ambiguity in language. Instead, we embed semantic concepts (or synsets) as defined in WordNet and represent a word token in a particular context by estimating a distribution over relevant semantic concepts. We use the new, context-sensitive embeddings in a model for predicting prepositional phrase(PP) attachments and jointly learn the concept embeddings and model parameters. We show that using context-sensitive embeddings improves the accuracy of the PP attachment model by 5.4% absolute points, which amounts to a 34.4% relative reduction in errors.