New answers tagged natural-language-processing
2
You don't need a powerful machine or a pre-trained model. All you need
— as Neil Slater rightly says in his comment to your question — is a corpus of English texts to analyse. There are some corpora available for linguistic research, or you can collect your own.
Then you need to split the texts into sentences, and tokenise them, and you're ready to calculate ...
0
The first step
You need to decide if you want to hold each string column or not. Then you must encode your text fields into numbers which you need to use some embedding algorithms like word2Vec. Check here.
Second step
Probably, you will have a lot of columns. Now, you need to reduce the dimension space. PCA, manifold transforms, partial least squares ...
1
This is just an implementation issue. One reason is the Huggingface implementation (which is not the original implementation by Google) wants to strictly separate the tokenization from the modeling. It is a convention that the input sequences are zero-padded, but in theory, it does not have to be so. In the Huggingface implementation, you use a different ...
0
Depending on the implementation you're using, you can adjust the granularity, which will influence how many clusters you will get.
See this description of MCL.
0
This is the task of so-called V&L (vision and language models) which effectively encode information from both worlds. There are also many training corpora covering this field already. Here is a quite recent paper on this: https://www.researchgate.net/publication/354617904_What_Vision-Language_Models_See'_when_they_See_Scenes
0
This is probably an issue of complete underfitting. How many training data do you use? What is your vocab size? What is your batch size and how many epochs did you train? Transformers always need more data than RNNs to reach good text quality.
0
There are other possible metrics, e.g. meteor and BLEURT.
They compensate some of the basic problems most researchers would like to avoid BLEU for. The downside of not using known metrics is, that your model is even harder to evaluate against other candidates. If you compare to human gold standard corpus, you should not count on BLEURT too much since it is ...
1
You could handwrite different templates and choose probabilistically, according to writing style or pragmatic effects like irony and so on, but that very much depends on the domain.
If you have tabular data, from which you want to generate text, you should probably forget about GPT and so on. You only have few control (despite copy mechanism) over the ...
1
What you want to look for is called anaphora resolution. You basically keep a record of the past conversation and try and find an antecedent for any occurrences of it, he/she, her/his, etc. You probably want to have a pre-processing step where you substitute the antecedent before passing the input sentence on to the agent.
Top 50 recent answers are included