SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1706.00286 · 2017

Learning to Compute Word Embeddings On the Fly

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1706.00286")
get_code_for_paper("1706.00286")
have("1706.00286")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1706.00286.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1706.00286.svg)](https://syntology.ai/paper/1706.00286)

Connect an agent — have() is free.