New answers tagged

1

Yes, you are correct and it was one of original motivations, which inspired the invention of the Attention mechanism in seq2seq problems https://arxiv.org/pdf/1706.03762.pdf. There is a quote from this paper: Recurrent models typically factor computation along the symbol positions of the input and output sequences. Aligning the positions to steps in ...


0

I think U are looking for PLSA for PLSA either U find out those topics(catogeries) with EM or NNMF Personally I recommend NNMF or u can use LDA which is Bayesian version of PLSA here is code for PLSA: https://github.com/Man-ash/Probabilistic-Latent-semantic-analysis which use NNMF for EM method I code it by myself but i am not sure if it is right https://...


1

DALL·E is a 12-billion parameter version of GPT-3 trained to generate images from text descriptions should be the same data they used to train the GPT-3


0

Human evaluation is the gold standard as stated in this podcast by Asli Celikyilmaz, even if you only test a very small part of the generated text. You needed an automated method and this one: BLEURT by Google would be helpful. It's a flexible, semantic-level metric/model trained in a multi-stage way: 1) masked language model like BERT; 2) pre-training on ...


0

It seems that Automated Knowledge Base Construction would be unfavorable. As Matt Gardner noted in NLP Highlights in 2019 that: Um, but I know that Google, for instance, canceled their knowledge base construction project because there wasn’t high enough precision to actually be useful in their product. The canceled project Knowledge Vault is an Automated ...


0

For the definition and calculation of perplexity, please refer to this answer. Google proposed a human evaluation metric called Sensibleness and Specificity Average (SSA) which combines two fundamental aspects of a humanlike chatbot: making sense and being specific. And they conducted some experiments and found that perplexity aligns very well with the SSA. ...


1

There are many ways to solve this problem. One way is to apply stemming or lemmatization to reduce your words. Using NLTK's Porter stemmer for example on healthy, healthier, healthiest, not healthy, more healthy, and zero healthy gives: healthi , healthier , healthiest , not healthi , more healthi , zero healthi This can help make word comparisons easier. ...


1

A critical goal of training a neural network is to minimize the loss. Loss is not explained for spaCy because it is a general concept for machine learning and deep learning. Loss is not specific to spaCy and although there are some finer details I don't believe that is your inquiry. In general, to understand loss functions, I recommend the following ...


1

The reason you would load a pre-existing model is that it offers something of value to your task (e.g. named entity recognition for food) and the cost of training it from scratch is not worth it. For example, to train GPT-3 from scratch would cost several million dollars. Typically someone will use a model like BERT and fine tune it. This is called ...


1

Since you want a shortcut use the spoonacular API. Below is a test with your words. You can see it had trouble with 'Coca' and 'veg'. What you need is 'named-entity recognition' for food. This is not a new thing but clearly not a solved problem. The Foodie Favorites repository attempts to solve the problem from scratch. If want to do some research and ...


0

There's nothing stopping you from training a model with whatever tags you want. Using what you describe as "usual" format means you would have approx half as many tags as using the IOB format. In theory this means your model will develop higher accuracy faster and with less training data. On the downside, you will need to do more work when ...


Top 50 recent answers are included