Unsupervised Lemmatization as Embeddings-Based Word Clustering
This addresses the problem of lemmatization for languages lacking annotated data, though it is incremental as it builds on existing clustering and similarity methods.
The paper tackles unsupervised lemmatization by grouping inflected word forms without annotated data, using a novel distance measure that combines word embedding similarity and edit distance, and shows promising results by surpassing baselines on 23 out of 28 datasets across 23 languages.
We focus on the task of unsupervised lemmatization, i.e. grouping together inflected forms of one word under one label (a lemma) without the use of annotated training data. We propose to perform agglomerative clustering of word forms with a novel distance measure. Our distance measure is based on the observation that inflections of the same word tend to be similar both string-wise and in meaning. We therefore combine word embedding cosine similarity, serving as a proxy to the meaning similarity, with Jaro-Winkler edit distance. Our experiments on 23 languages show our approach to be promising, surpassing the baseline on 23 of the 28 evaluation datasets.