Introducing state of the art text classification with universal language models · fast.ai NLP


18 bookmarks. First posted by Sylphe 9 days ago.


Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch. We propose Universal Language Model Fine-tuning (ULMFiT), an effective transfer learning method that can be applied to any task in NLP, and introduce techniques that are key for fine-tuning a language model. Our method significantly outperforms the state-of-the-art on six text classification tasks, reducing the error by 18-24% on the majority of datasets. Furthermore, with only 100 labeled examples, it matches the performance of training from scratch on 100x more data. We open-source our pretrained models and code.
ML  NLP  text  classification  fastai 
5 days ago by foodbaby
“This method dramatically improves over previous approaches to text classification, and the code and pre-trained models allow anyone to leverage this new approach to better solve problems such as:

Finding documents relevant to a legal case;
Identifying spam, bots, and offensive comments;
Classifying positive and negative reviews of a product;
Grouping articles by political orientation;
…and much more.”
7 days ago by sshappell
This post is a lay-person’s introduction to our new paper, which shows how to classify documents automatically with both higher accuracy and less data requirements than previous approaches. via Pocket
IFTTT  Pocket 
8 days ago by roolio
This post shows how to classify documents automatically with both higher accuracy and less data requirements than previous approaches. It explains in simple terms: natural language processing; text classification; transfer learning; language modeling; and how this approach brings these ideas together.
algorithms  nlp  machinelearning  classification 
8 days ago by peterb
the code and pre-trained models allow anyone to leverage this new approach to better solve problems such as:

- Finding documents relevant to a legal case;
- Identifying spam, bots, and offensive comments;
- Classifying positive and negative reviews of a product;
- Grouping articles by political orientation;
- …and much more.

In computer vision the success of transfer learning and availability of pre-trained Imagenet models has transformed the field. Many people including entrepreneurs, scienti...
nlp  machine-learning  ai  transfer-learning  ml  fast.ai  classification 
9 days ago by hellsten
This post is a lay-person’s introduction to our new paper, which shows how to classify documents automatically with both higher accuracy and less data requirements than previous approaches. via Pocket
Pocket 
9 days ago by slightlywinded
“This method dramatically improves over previous approaches to text classification, and the code and pre-trained models allow anyone to leverage this new approach to better solve problems such as:

Finding documents relevant to a legal case;
Identifying spam, bots, and offensive comments;
Classifying positive and negative reviews of a product;
Grouping articles by political orientation;
…and much more.”
fast.ai  text_classification  machine_learning 
9 days ago by Sylphe