Expand / Collapse search
Watch TV
Menu

This material may not be published, broadcast, rewritten, or redistributed. ©2023 FOX News Network, LLC. All rights reserved. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset. Powered and implemented by FactSet Digital Solutions. Legal Statement. Mutual Fund and ETF data provided by Refinitiv Lipper.

Google
Published

Google's Parsey McParseface (yep) will help AI understand English

By Chloe Albanesius | PCmag
A logo is pictured at Google's European Engineering Center in Zurich April16, 2015. (REUTERS/Arnd Wiegmann)

A logo is pictured at Google's European Engineering Center in Zurich April16, 2015. (REUTERS/Arnd Wiegmann)

Boaty McBoatface was so last week; this week it's Parsey McParseface, courtesy of Google.

The search giant this week open-sourced its neural network framework, SyntaxNet, which includes English parser Parsey McParseface, a tool developers can use to analyze English text. Translation: developers will be able to fiddle with the underlying technology powering Google's powerful natural language software so that apps and voice assistants and robots can better understand what English-speaking users want.

"One of the main problems that makes parsing so challenging is that human languages show remarkable levels of ambiguity," Google says in a blog post. "It is not uncommon for moderate length sentences—say 20 or 30 words in length—to have hundreds, thousands, or even tens of thousands of possible syntactic structures. A natural language parser must somehow search through all of these alternatives, and find the most plausible structure given the context."

That's why talking to Siri, Cortana, or Google Now isn't like talking to another human being just yet. "Humans do a remarkable job of dealing with ambiguity, almost to the point where the problem is unnoticeable; the challenge is for computers to do the same," Google says.

According to Google, Parsey McParseface can understand English newswire sentences with over 94 percent accuracy. "This suggests that we are approaching human performance—but only on well-formed text. Sentences drawn from the web are a lot harder to analyze," but still have 90 percent accuracy.

"But our work is still cut out for us: we would like to develop methods that can learn world knowledge and enable equal understanding of natural language across all languages and contexts," Google says.

In opening up its research to the public, "we hope that it will be useful to developers and researchers interested in automatic extraction of information, translation, and other core applications of NLU," according to Google.

This article originally appeared on PCMag.com.