Learning to Compute Word Embeddings On the Fly



Words in natural language follow a Zipfian distribution whereby some words are frequent but most are rare. Learning representations for words in the “long tail” of this distribution requires enormous amounts of data. Representations of rare words trained directly on end tasks are usually poor, requiring us to pre-train embeddings on external data, or treat all rare words as out-of-vocabulary words with a unique representation. We provide a method for predicting embeddings of rare words on the fly from small amounts of auxiliary data with a network trained end-to-end for the downstream task. We show that this improves results against baselines where embeddings are trained on the end task for reading comprehension, recognizing textual entailment and language modeling.

Related Publications

All Publications

Unsupervised Translation of Programming Languages

Baptiste Roziere, Marie-Anne Lachaux, Lowik Chanussot, Guillaume Lample

NeurIPS - December 1, 2020

Learning Reasoning Strategies in End-to-End Differentiable Proving

Pasquale Minervini, Sebastian Riedel, Pontus Stenetorp, Edward Grefenstette, Tim Rocktäschel

ICML - August 13, 2020

Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing

Xilun Chen, Asish Ghoshal, Yashar Mehdad, Luke Zettlemoyer, Sonal Gupta

EMNLP - October 7, 2020

Voice Separation with an Unknown Number of Multiple Speakers

Eliya Nachmani, Yossi Adi, Lior Wolf

ICML - October 1, 2020

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy