# No Word is an Island -- A Transformation Weighting Model for Semantic Composition

## TL;DR

This paper introduces TransWeight, a transformation weighting model for semantic composition that outperforms existing models across multiple languages while significantly reducing parameter count by grouping similar words for composition.

## Contribution

The paper presents a novel composition model that balances parameter efficiency with high performance across different phrase types and languages.

## Key findings

- TransWeight outperforms existing models on nominal compounds and adjective phrases.
- It reduces the number of parameters needed compared to previous models.
- The model is effective across English, German, and Dutch.

## Abstract

Composition models of distributional semantics are used to construct phrase representations from the representations of their words. Composition models are typically situated on two ends of a spectrum. They either have a small number of parameters but compose all phrases in the same way, or they perform word-specific compositions at the cost of a far larger number of parameters. In this paper we propose transformation weighting (TransWeight), a composition model that consistently outperforms existing models on nominal compounds, adjective-noun phrases and adverb-adjective phrases in English, German and Dutch. TransWeight drastically reduces the number of parameters needed compared to the best model in the literature by composing similar words in the same way.