Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Learning to Compute Word Embeddings On the Fly
Dzmitry Bahdanau, Tom Bosc, Stanisław Jastrzębski, Edward Grefenstette, Pascal Vincent, Yoshua Bengio
Feb 15, 2018 (modified: Feb 15, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract: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.
TL;DR:We propose a method to deal with rare words by computing their embedding from definitions.
Keywords:NLU, word embeddings, representation learning
Enter your feedback below and we'll get back to you as soon as possible.