Aleksandr Drozd

Subword-level Composition Functions for Learning Word Embeddings

2018

Subword-level information is crucial for capturing the meaning and morphology of words, especially for out-of-vocabulary entries. We propose CNN-and RNN-based subword-level composition functions for learning word embeddings, and systematically compare them with popular word-level and …

Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn't.

2016

Following up on numerous reports of analogybased identification of "linguistic regularities" in word embeddings, this study applies the widely used vector offset method to 4 types of linguistic relations: inflectional and derivational morphology, and lexicographic …

Word Embeddings, Analogies, and Machine Learning: Beyond king - man + woman = queen.

2016 · IT University Of Copenhagen (IT University of Copenhagen)

Solving word analogies became one of the most popular benchmarks for word embeddings on the assumption that linear relations between word pairs (such as king:man :: woman:queen) are indicative of the quality of the embedding. …

The (too Many) Problems of Analogical Reasoning with Word Vectors

2017

This paper explores the possibilities of analogical reasoning with vector space models. Given two pairs of words with the same relation (e.g. man:woman :: king:queen), it was proposed that the offset between one pair of …