# Morphological Word Embeddings

## TL;DR

This paper introduces a semi-supervised approach to guide word embeddings with morphological data, encouraging the embeddings to encode morphological features, demonstrated through experiments on German.

## Contribution

It extends the log-bilinear model to incorporate morphological annotations, enabling embeddings to better capture morphological similarities.

## Key findings

- Embeddings encode morphological features effectively.
- The method improves morphological similarity representation.
- Demonstrated on German language data.

## Abstract

Linguistic similarity is multi-faceted. For instance, two words may be similar with respect to semantics, syntax, or morphology inter alia. Continuous word-embeddings have been shown to capture most of these shades of similarity to some degree. This work considers guiding word-embeddings with morphologically annotated data, a form of semi-supervised learning, encouraging the vectors to encode a word's morphology, i.e., words close in the embedded space share morphological features. We extend the log-bilinear model to this end and show that indeed our learned embeddings achieve this, using German as a case study.