Facebook has unveiled DeepText, a deep learning-based text comprehension engine that uses neural networks to understand the context of posts in over 20 languages.
DeepText uses several deep learning neural network architectures, as well as its artificial intelligence (AI) backbone FBLearner Flow and the Torch open source machine learning library, to perform word-level and character-based learning.
The system can understand slang and make sense of potentially ambiguous phrases. For example, if a Facebook user posts the phrase ‘I like apple’ DeepText can work out whether it refers to the fruit or Apple.
Facebook had to go beyond normal neuro-linguistic programming (NLP) techniques with DeepText, as the extensive pre-processing logic built on top of intricate software engineering and language knowledge is ineffective at picking up variations in languages and spelling when people post on the same topic.
Neural network deep learning allows DeepText to learn as it sifts through Facebook posts, bypassing the need to rely on pre-programmed language-dependant knowledge.
“In traditional NLP approaches, words are converted into a format that a computer algorithm can learn. The word 'brother' might be assigned an integer ID such as 4598, while the word 'bro' becomes another integer, like 986665. This representation requires each word to be seen with exact spellings in the training data to be understood,” Facebook explained.
“With deep learning, we can instead use 'word embeddings', a mathematical concept that preserves the semantic relationship among words. So, when calculated properly we can see that the word embeddings of 'brother' and 'bro' are close in space. This type of representation allows us to capture the deeper semantic meaning of words.”
DeepText is being tested across Facebook’s various services, including Messenger, which is helping it to become smarter, such as understanding when someone might be expressing a desire to go somewhere.
Facebook sees potential for DeepText to improve the experiences of Facebook users, for example by automatically detecting and removing spam posts or displaying the most relevant comments.
Facebook’s work on deep learning technologies is pertinent given that the company is developing an AI-powered virtual assistant called M for Messenger that mixes advanced machine learning with human customer service.
Could be used for everything from search-and-rescue robots to wearable tech
Don't require the rare material being mined from the mountains of South America
IBM hopes that its new tool will avoid bias in artificial intelligence
Found by calculating the strength of the material deep inside the crust of neutron stars