MoRTy: Unsupervised Learning of Task-specialized Word Embeddings by Autoencoding

Nils Rethmeier, Barbara Plank

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review


Word embeddings have undoubtedly revolutionized NLP. However, pre-trained embeddings do not always work for a specific
task (or set of tasks), particularly in limited resource setups. We introduce a simple
yet effective, self-supervised post-processing
method that constructs task-specialized word
representations by picking from a menu of
reconstructing transformations to yield improved end-task performance (MORTY). The
method is complementary to recent state-of-the-art approaches to inductive transfer via
fine-tuning, and forgoes costly model architectures and annotation. We evaluate MORTY
on a broad range of setups, including different
word embedding methods, corpus sizes and
end-task semantics. Finally, we provide a surprisingly simple recipe to obtain specialized
embeddings that better fit end-tasks
Original languageEnglish
Title of host publicationProceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)) : RepL4NLP-2019
Place of PublicationFlorence
PublisherAssociation for Computational Linguistics
Publication date2019
ISBN (Electronic) 978-1-950737-35-2
Publication statusPublished - 2019


Dive into the research topics of 'MoRTy: Unsupervised Learning of Task-specialized Word Embeddings by Autoencoding'. Together they form a unique fingerprint.

Cite this