Tags: embedding*

0 bookmark(s) - Sort by: Date ↓ / Title /

  1. With deep learning, the ROI for having clean and high quality data is immense, and this is realized in every phase of training. For context, the era right before BERT in the text classification world was one where you wanted an abundance of data, even at the expense of quality. It was more important to have representation via examples than for the examples to be perfect. This is because many Al systems did not use pre-trained embeddings (or they weren't any good, anyway) that could be leveraged by a model to apply practical generalizability. In 2018, BERT was a breakthrough for down-stream text tasks,
    2023-11-11 Tags: , , , , by klotz
  2. LangChain has many advanced retrieval methods to help address these challenges. (1) Multi representation indexing: Create a document representation (like a summary) that is well-suited for retrieval (read about this using the Multi Vector Retriever in a blog post from last week). (2) Query transformation: in this post, we'll review a few approaches to transform humans questions in order to improve retrieval. (3) Query construction: convert human question into a particular query syntax or language, which will be covered in a future post
    2023-10-26 Tags: , , , by klotz
  3. Unlock advanced customer segmentation techniques using LLMs, and improve your clustering models with advanced techniques
  4. Zero-Shot Classification
    To perform zero shot classification, we want to predict labels for our samples without any training. To do this, we can simply embed short descriptions of each label, such as positive and negative, and then compare the cosine distance between embeddings of samples and label descriptions.

    As shown above, zero-shot classification with embeddings can lead to great results, especially when the labels are more descriptive than just simple words.

    The highest similarity label to the sample input is the predicted label. We can also define a prediction score to be the difference between the cosine distance to the positive and to the negative label. This score can be used for plotting a precision-recall curve, which can be used to select a different tradeoff between precision and recall, by selecting a different threshold.

Top of the page

First / Previous / Next / Last / Page 1 of 0 SemanticScuttle - klotz.me: tagged with "embedding"

About - Propulsed by SemanticScuttle