U.S. social networking company LinkedIn has released DeText, an open source natural language processing framework that uses deep neural networks to facilitate tasks such as search and recommendation ranking, multiclass classification, query understanding, and sequence completion.

So what does DeText add to the ever-growing field of machine learning? As one might imagine, getting machines to understand human language isn’t as easy as it might initially appear — different word choices and contexts can all add to the complexity of any given utterance. In the field of artificial intelligence, natural language processing (NLP) is what machines use to read, understand and derive meaning from human language. Well-known NLP models include Bidirectional Encoder Representations from Transformers or BERT, which allow machines to perform tasks like machine translation, speech recognition, text classification, and more. When put into practice, such models can extract data from the internet to automate research, or detect disinformation.

Not surprisingly though, such tasks can require quite a bit of computational power to perform, depending on the AI model used. “DeText is a framework for efficiently leveraging deep learning models (such as BERT) to understand the semantics of text data,” as LinkedIn senior engineering manager Weiwei Guo explained to us via email. “It is able to perform word sense disambiguation and identify similar words such as ‘software developer’ versus ‘programmer.’ BERT models require a large amount of computation time, so our focus in building and productionizing BERT-based DeText models has been to simplify the process of using BERT in commercial applications.”

Flexible and Swappable

To tackle this issue of computational inefficiency, DeText has been designed with flexibility in mind, so that different NLP models can be “swapped” in as needed, depending on the requirements of different production processes. For instance, DeText supports a range of state-of-the-art semantics understanding models like convolutional neural networks (CNNs), long short-term memory networks (LSTMs), as well as BERT.

“The ‘swappability’ component is what enables the wide applicability of the DeText framework,” said Guo. “In addition, users can conveniently search for the optimal network architecture for use in their applications.”

#development #machine learning #news #deep learning #deep learning