SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.11749 · ICML · 2021

Paraphrases do not explain word analogies

Louis Fournier, Ewan Dunbar

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. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Many types of distributional word embeddings (weakly) encode linguistic regularities as directions (the difference between jump and jumped will be in a similar direction to that of walk and walked, and so on). Several attempts have been made to explain this fact. We respond to Allen and Hospedales' recent (ICML, 2019) theoretical explanation, which claims that word2vec and GloVe will encode linguistic regularities whenever a specific relation of paraphrase holds between the four words involved in the regularity. We demonstrate that the explanation does not go through: the paraphrase relations needed under this explanation do not hold empirically.

For agents

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

get_harvested_code_for_paper("2102.11749")
get_code_for_paper("2102.11749")
have("2102.11749")

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

curl https://syntology.ai/api/ran/2102.11749.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.11749.svg)](https://syntology.ai/paper/2102.11749)

Connect an agent — have() is free.