5

I will be starting my PhD in natural language processing in a few days and this is very similar to my proposed topic. It's an open problem that ties NLP and AI into philosophy of science and epistemology and is, I think, extremely interesting. I say all this to drive home the point that this is not a simple problem. Two major theoretical concerns come to my ...


4

Lorem ipsum generators don't typically use anything considered as AI. Usually they just store large pieces of text and select sections from it randomly - they are very simple. The main goal is to produce "nonsense" text that fills space but does not distract from issues of layout and design. The variations of it are usually just for fun, and like the ...


3

If you wanted to generate more I guess you could take the string and convert to a list then you could randomly select as many words as you want, from the list. Using Python import numpy as np lorem = "lLorem ipsum dolor sit amet, consectetur adipiscing elit. ".split() number_of_words_needed = 20 new_text = [] for i in range(number_of_words_needed): ...


3

Summarizing text is always going to be 'easier or more efficient' than voice simply because voice requires the additional step of converting to text. That doesn't tell you anything about accuracy. From an article published on June 1, 2017, Google’s speech recognition is now almost as accurate as humans: "According to Mary Meeker’s annual Internet Trends ...


2

This seems like a problem for the use of an encoder-decoder pair such as those seen in text summarization (see this paper by Rush et al.: https://arxiv.org/pdf/1509.00685.pdfï%C2%BC). You would need the following layers: LSTM layer to encode the given input text into an embedding LSTM layer the looks over the currently generated output to encode the ...


2

The ability to re-frame summarization as a problem for ANN is rather dependent on what kind of output you're looking for: you mentioned 'salient parts of the text'. One possibly is to use a deep learning approach that first chunks together words that belong in the same phrase as a single 'feature'. Another possibility is to identify both key words and ...


2

Genuine success in this area would be beyond the state-of-the-art in research, since it likely requires analogising from relational knowledge extracted from text. In recent years, techniques for working with natural language have tended to be statistical, and are therefore somewhat deficient in this respect. You could look at 'bag of words'/latent semantic ...


1

This is a difficult problem. First, how do you define 'subject'? Do you have a (closed) lists of labels you want to assign? What about subjects that overlap, or don't occur in your list? What even is a subject? This is a non-trivial issue. Second, and this is even harder, how do you want to recognise subjects? A simple solution could be using a list of ...


1

As Andreas has commented this is a problem of statistical language model (a probability distribution over a sequence of words). The important thing you need is a hash table mapping fixed-length to the expected ending chains of words in your dictionary. Things that can make your prediction better: Add better and more words to your dictionary. Use text ...


1

I am sure there are complex methods to extract keywords, but the standard one which should serve as a strong baseline is the RAKE graph algorithm https://pypi.org/project/rake-nltk/. It should work reasonably well in most text domains.


1

I think you should use Keras embedding layer. It will be too easier than what you are doing. Steps Create Embedding Matrix add matrix to embedding layer while building model. You will find detailed article https://www.cs.uaf.edu/2011/spring/cs641/lecture/04_05_modeling.html


1

Briefly: I think what you are looking for is an RNN network (Either LSTM or GRU) with the many-to-many topology. Explanation: Clearly your input is the sentences (or to be more precise, the an embedding of your sentences, because you cannot feed the raw text to the network). then for each sentence you want to assign a value, which means for n inputs, you ...


1

Just to elaborate my brief comment on the question: Identifying the primary concepts of a paragraph required understanding of the meaning of the text. In natural language processing we are still a long way off even recognising and representing the meaning of text, let alone summarising the meaning of multiple sentences into a single statement. Note that ...


1

If you're looking for an existing solution, the best approach I found was using a TF-IDF model, check out the links below which have similar examples which should be easily adapted for your dataset. https://www.kaggle.com/selener/multi-class-text-classification-tfidf#targetText=Text%20classification%20(multiclass)&targetText=With%20the%20aim%20to%...


1

My first recommendation would be before you create an AI or ML based solution. Kindly consider using a business Q&A Software such as Questions for Confluence by Atlassian among others. An enterprise multiple choice solution could be a simple and elegant fit for this problem. However, if one was to design a solution in accordance to your specification ...


Only top voted, non community-wiki answers of a minimum length are eligible