|Apache Adds ONNX Runtime To OpenNLP|
|Written by Kay Ewbank|
|Monday, 19 September 2022|
Apache has added the ONNX Runtime to Apache OpenNLP. The addition works towards the goal of OpenNLP to bridge the gap between modern deep learning NLP models and Apache OpenNLP’s ease of use as a Java NLP library.
Apache OpenNLP is an open source machine learning library for natural language processing (NLP) for Java. It is used by a number of Apache open source applications, including Apache Solr, Apache UIMA, and Apache Lucene, as well as many commercial and research applications.
OpenNLP provides NLP capabilities for sentence detection, tokenization, parts-of-speech, lemmatization, language detection, and named-entity recognition using maximum entropy and perceptron-based algorithms. The Apache OpenNLP library contains several components that can be combined to build a full natural language processing pipeline. Components contain parts that can be used to execute the respective natural language processing task, to train a model and often also to evaluate a model. Each of these facilities is accessible via its API,
Apache OpenNLP’s NLP maximum entropy and perceptron model training methods have relatively low overhead, and can be trained without the need for GPUs, but the developers admit that the trained models can fall short of the performance of modern NLP models that use the transformer architecture.
The addition of ONNX Runtime is designed to overcome this. ONNX Runtime is a runtime accelerator for models trained from deep learning frameworks that is optimized for performance. With Apache OpenNLP 2.0, transformer-based models, such as those available through the Hugging Face Hub, can be converted to ONNX and used directly from Apache OpenNLP via ONNX Runtime.
The Hugging Face Hub is a platform with over 60K models, 6K datasets, and 6K demos in which people can collaborate in their ML workflows. The Hub works as a central place where anyone can share, explore, discover, and experiment with open-source machine learning.
Apache OpenNLP 2.0 is available now.
or email your comment to: firstname.lastname@example.org
|Last Updated ( Monday, 19 September 2022 )|