Google has released SyntaxNet, a natural-language neural network framework for helping machines understand natural language, as an open-source offering.
Advertisement
One of the things that makes parsing so challenging for computers is that human languages show remarkable levels of ambiguity. According to Google, it is common for sentences of around 20 words to have thousands of different possible syntactic structures. A natural language parser must somehow search through all of these alternatives, and find the most plausible structure given the context..
“Because Parsey McParseface is the most accurate such model in the world, we hope that it will be useful to developers and researchers interested in automatic extraction of information, translation, and other core applications of NLU”, senior staff research scientist Slav Petrov wrote yesterday on the Google Research Blog. During the eighteenth and nineteenth centuries, students took parsing courses where they would break down the grammatical structure of sentence in order to understand its exact meaning.
“For the sake of simplicity, let us consider an example sentence – ‘Alice saw Bob”.
Natural language understanding is traditionally very hard to achieve with computers.
Machine learning (and in particular, neural networks) have made significant progress in resolving these ambiguities [problems like the one described above]. Maybe those involved wished to imply just how complex the topic of AI itself is though the parser itself forms part of what Google refers to as the SyntaxNet, the open-source neural network framework.
‘Parsey McParseface recovers individual dependencies between words with over 94% accuracy, beating our own previous state-of-the-art results, which were already better than any previous approach. Parsey is also accurate on about 90 percent of the case with sentences randomly drawn from the web.
When presented with this sentence, Parsey McParseface was able to analyse this correctly. Parsers are what allow applications like Google Now and Siri to understand the words you are either speaking or typing, label each word by its syntax and then discern your intent from what you’ve said/typed.
Advertisement
SyntaxNet and Parsey McParseface processes sentences left to right so dependencies are added incrementally and given scores based on the plausibility.
