# Contextual Compositionality Detection with External Knowledge Bases andWord Embeddings

## TL;DR

This paper proposes a contextual approach to detect phrase compositionality by enriching word embeddings with external knowledge and contextual evidence, improving accuracy over existing methods.

## Contribution

It introduces a novel method that combines local and global context with external knowledge bases to detect phrase compositionality in a non-deterministic, context-dependent manner.

## Key findings

- Outperforms state-of-the-art baselines in compositionality detection
- Effectively incorporates external knowledge and contextual information
- Demonstrates significant improvement on crowdsourced dataset

## Abstract

When the meaning of a phrase cannot be inferred from the individual meanings of its words (e.g., hot dog), that phrase is said to be non-compositional. Automatic compositionality detection in multi-word phrases is critical in any application of semantic processing, such as search engines; failing to detect non-compositional phrases can hurt system effectiveness notably. Existing research treats phrases as either compositional or non-compositional in a deterministic manner. In this paper, we operationalize the viewpoint that compositionality is contextual rather than deterministic, i.e., that whether a phrase is compositional or non-compositional depends on its context. For example, the phrase `green card' is compositional when referring to a green colored card, whereas it is non-compositional when meaning permanent residence authorization. We address the challenge of detecting this type of contextual compositionality as follows: given a multi-word phrase, we enrich the word embedding representing its semantics with evidence about its global context (terms it often collocates with) as well as its local context (narratives where that phrase is used, which we call usage scenarios). We further extend this representation with information extracted from external knowledge bases. The resulting representation incorporates both localized context and more general usage of the phrase and allows to detect its compositionality in a non-deterministic and contextual way. Empirical evaluation of our model on a dataset of phrase compositionality, manually collected by crowdsourcing contextual compositionality assessments, shows that our model outperforms state-of-the-art baselines notably on detecting phrase compositionality.