Crossword-solving AI system to help machines learn language

Scientists have developed a web-based artificial intelligence (AI) platform which uses deep learning approach to solve crossword puzzles and could help machines understand language more effectively.
The system can answer standard crossword clues better than existing commercial products specifically designed for the task, researchers said.
The system can also be used as a 'reverse dictionary' in which the user describes a concept and the system returns possible words to describe that concept, researchers said.
The researchers used the definitions contained in six dictionaries, and Wikipedia, to 'train' the system so that it could understand words, phrases and sentences - using the definitions as a bridge between words and sentences.

Their results suggest that a similar approach may lead to improved output from more general language understanding and dialogue systems and information retrieval engines in general.
"Over the past few years, there has been a mini-revolution in machine learning," said Felix Hill of the University of Cambridge in UK.

"We're seeing a lot more usage of deep learning, which is especially useful for language perception and speech recognition," Hill said.
Deep learning is an approach in which artificial neural networks with little or no prior 'knowledge' are trained to recreate human abilities using massive amounts of data.
"Dictionaries contain just about enough examples to make deep learning viable, but we noticed that the models get better and better the more examples you give them," said Hill.

"Our experiments show that definitions contain a valuable signal for helping models to interpret and represent the meaning of phrases and sentences," said Hill.
Researchers used the model as a way of bridging the gap between machines that understand the meanings of individual words and machines that can understand the meanings of phrases and sentences.
"Our system can't go too far beyond the dictionary data on which it was trained, but the ways in which it can are interesting, and make it a surprisingly robust question and answer system - and quite good at solving crossword puzzles," said Hill.
While it was not built with the purpose of solving crossword puzzles, the researchers found that it performed better than products that are engineered for the task.

Existing commercial crossword-answering applications function in a similar way to a Google search, with one system able to reference over 1,100 dictionaries.
While this approach has advantages if you want to look up a definition verbatim, it works less well when you input a question or query that the model has never seen in training.
It also makes it incredibly 'heavy' in terms of the amount of memory it requires.
The study was published in the journal Transactions of the Association for Computational Linguistics.