-
Tips for becoming a good boxer - November 6, 2020
-
7 expert tips for making your hens night a memorable one - November 6, 2020
-
5 reasons to host your Christmas party on a cruise boat - November 6, 2020
-
What to do when you’re charged with a crime - November 6, 2020
-
Should you get one or multiple dogs? Here’s all you need to know - November 3, 2020
-
A Guide: How to Build Your Very Own Magic Mirror - February 14, 2019
-
Our Top Inspirational Baseball Stars - November 24, 2018
-
Five Tech Tools That Will Help You Turn Your Blog into a Business - November 24, 2018
-
How to Indulge on Vacation without Expanding Your Waist - November 9, 2018
-
5 Strategies for Businesses to Appeal to Today’s Increasingly Mobile-Crazed Customers - November 9, 2018
Google shares software tool for understanding language – and it’s called Parsey McParseface
It’s a significant boost for anyone trying to get computers to understand natural language, and could be key to the future of artificial intelligence.
Advertisement
Parsey McParseface uses machine learning algorithms to analyse the structure of human language. Googly McSearchface senior staff research scientist Slav Petrov says a neural network is needed because “human languages show remarkable levels of ambiguity”. It also comes with Parsey McParseface, an English language parsing model that Google claims is the most accurate model available. In computing, parsing is the process of analysing a string of symbols to understand the exact meaning of a sentence. An input sentence is processed from left to right, with dependencies between words being incrementally added as each word in the sentence is considered.
Parsey McParseface is a piece of a larger framework called SyntaxNet, itself a big part of Google’s popular home-built TensorFlow software for building artificial intelligence, as explained in a blog entry.
So, Parsey McParseface can explain the functional role of each word in a given sentence. After all, language is complicated: Consider that “Buffalo buffalo Buffalo buffalo buffalo buffalo” is a 100% gramatically correct sentence in American English.
‘This suggests that we are approaching human performance-but only on well-formed text.
The structure encodes that Alice and Bob are nouns and saw is a verb.
But in more complex examples, where sentences can be 20 to 30 words in length, there can be hundreds or even thousands of possible syntactic structures.
However, government ministers and officials were not impressed and instead the vessel was named after the broadcaster Sir David Attenborough with a submersible being called Boaty McBoatface. Among other tasks, Google’s parser has to determine whether or not the street referred to is actually in Alice’s auto, a effect of ambiguity of the object to which the prepositional phrase in her vehicle is attached.
Advertisement
But if you’re an average computer, just following instructions, and you’re doing sentence diagrams, it is totally gramatically correct to parse that sentence as saying the street was located in Alice’s vehicle.