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

Nils Rethmeier, Barbara Plank


Abstract
Word embeddings have undoubtedly revolutionized NLP. However, pretrained 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.
Anthology ID:
W19-4307
Volume:
Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Isabelle Augenstein, Spandana Gella, Sebastian Ruder, Katharina Kann, Burcu Can, Johannes Welbl, Alexis Conneau, Xiang Ren, Marek Rei
Venue:
RepL4NLP
SIG:
SIGREP
Publisher:
Association for Computational Linguistics
Note:
Pages:
49–54
Language:
URL:
https://aclanthology.org/W19-4307
DOI:
10.18653/v1/W19-4307
Bibkey:
Cite (ACL):
Nils Rethmeier and Barbara Plank. 2019. MoRTy: Unsupervised Learning of Task-specialized Word Embeddings by Autoencoding. In Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019), pages 49–54, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
MoRTy: Unsupervised Learning of Task-specialized Word Embeddings by Autoencoding (Rethmeier & Plank, RepL4NLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-4307.pdf
Code
 NilsRethmeier/MoRTy