4
votes
How to go about classifying 1000 classes?
If you are asking for arbitrary ML task dealing with 1000+ classes the most straigtforward thing that comes to mind is the ImageNet - https://en.wikipedia.org/wiki/...
- 2,194
4
votes
Accepted
Top Frequent occurrence word effect in Model Efficiency?
As far as I know, there are few aspects that would probably improve the model score:
Normalization
Lemmatization
Stopwords removal (as you asked here)
Based on your question, "is ...
- 166
4
votes
Top Frequent occurrence word effect in Model Efficiency?
Based on my experience, I did 2 tasks that is proven to improve the accuracy/score of my model.
Normalization
removing characters and symbols in a text
lowercase folding
Stopwords removal (as what ...
3
votes
Is it possible to derive meaning from text by providing multiple ways of saying the same thing to a neural network?
No, it will not derive patterns of meaning, as the network has no understanding of language. What will happen, is that it picks up surface features (usually letter sequences) which are common between ...
- 5,262
3
votes
Accepted
How to use LSTM to generate a paragraph
Take the sentence that was generated by your LSTM and feed it back into the LSTM as input. Then the LSTM will generate the next sentence. So the LSTM is using it's previous output as it's input. That'...
- 182
2
votes
What is the most accurate pretrained sentiment analysis model by 2019?
For best results, I'd recommend Google Cloud Machine Learning. It has [Natural Language Processing API] (https://cloud.google.com/natural-language/docs/basics) with Sentiment, Entity, and Entity-...
- 59
2
votes
Accepted
Is a dataset of roughly 700 sentences of an average length of 15 words enough for text classification?
It depends on the number of classes; we are getting good results with about 40 training examples per class.
A good way to get an idea about this is to run a test with an increasing set of training ...
- 5,262
2
votes
Does summing up word vectors destroy their meaning?
Summing up a sequence of word vector maybe used in practice sometimes. However, the operation of addition is non-reversible, meaning that once you sum up a few numbers, you cannot get the original ...
- 1,725
2
votes
Distinguishing text with opposite meanings in SVM (False Information Detection)
Going step by step:
Preprocessing
Preprocessing is a big deal in NLP, out there you'll find many tutorials describing the classic steps but few explanations about why and when you should actually ...
- 4,773
2
votes
How to use LSTM to generate a paragraph
As you know, an LSTM language model takes in the past word and tries to predict the new one and continue over a loop. A sentence is divided into tokens and depending on different method, the tokens ...
- 1,725
2
votes
Is there an AI that can extract proper nouns from free text?
This is a hard problem, unless you have a list of proper nouns you want to recognise. If John Allen is in this list, then you can easily use a longest match to prefer it over John or Allen. The same ...
- 5,262
2
votes
Accepted
How to predict the rating of a text review and improve it?
Why is it better to treat the rating prediction of a text review as a regression problem rather than a classification one? Is it because the ratings (1,2,3,4,5) are ordinal variables?
Well, the main ...
- 170
2
votes
How do I use ResNet for text processing?
ResNet as a name is defined as a CNN with a specific architecture, but the more general concept of Residual Networks are not necessarily CNNs, but networks that use skip connections.
You could make a ...
- 1,112
1
vote
Using a pre-trained model to generate labels to data to then train a model on
If using BART is already giving you good results, why do you need a new model?
Not a rhetorical question. You might have good reasons for that. Training a model with less parameters optimized only on ...
- 4,773
1
vote
Accepted
Which algorithm can be used for extracting text patterns in tabular data?
You should first segregate the rejected samples. You can use then use string matching or something more complex (like creating embeddings and then, taking L2 distance between them) between the ...
- 848
1
vote
Which pre-processing steps are necessary for Deep Learning models to solve a document classification problem?
It depends on the type of model you use and the task, you are attempting to solve.
Almost all the preprocessing steps that you mention remove some information from the text. If you think the removed ...
- 241
1
vote
Get the name of a merchant from records
The problem:
You are facing a Natural Language problem called Named Entity Recognition (that's the key word you are looking for).
But before you dive deep into it, have in mind it's best suited for ...
- 824
1
vote
Training and Evaluating BERT and XLNET
You’ll want a reasonable GPU (probably 8GB+), but otherwise no special hardware needed.* You may need to tune down sequence length and batch size to fit your GPU; RAM will be the limiting factor. Don’...
- 266
1
vote
Accepted
Can I use one-hot vectors for text classification?
One hot encoding is a good strategy to apply with categorical variables that assume few possible values. The problem with text data is that you easily end up with corpora with a really large ...
- 4,773
1
vote
Accepted
How do RNN's for sentiment classification deal with different sentence lengths?
One of the essential pre-processing we do on the corpus involves treating the variable-length sentences to a fixed length. There are various ways in which we can do this:
Truncate
This involves ...
- 738
1
vote
Accepted
Text classification of non-equal length texts, should I pad left or right?
For any model that does not take a time series approach like an RNN does, the padding shouldn't make a difference.
I prefer padding right simply because there also might be text you need to cut-off. ...
- 256
1
vote
NLP Identifying important key words in a corpus
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 ...
- 89
1
vote
Top Frequent occurrence word effect in Model Efficiency?
Based on my project, there is how i clean and doing some preparation on the data.
Delete specific charaters ('\r', '\n', '"',)
Change into the lowercase
Delete some symbols
Lemmatization (change ...
1
vote
Top Frequent occurrence word effect in Model Efficiency?
The technical term for these words is "stop words". Have a look at Information Retrieval and indexing (eg TF/IDF) to make up your mind whether you want to remove them or not.
- 5,262
1
vote
Can artificial intelligence classify textual records?
AI can categorize documents very accurately. It is not a new application but in the last year the accuracy of the underlying algorithms such as text classifiers, and language models in general, has ...
- 1,698
1
vote
When is it time to switch to deep neural networks from simple networks in text classification problems?
Source: https://blog.easysol.net/building-ai-applications/
When data is too big, complex and nonlinear it's time to try deep learning. It's always good to try to add some layers to see it can ...
- 857
1
vote
How does the weight update formula for logistic regression work?
I think i found out how that works, so i made a short article about it .
https://medium.com/@kourloskostas/python-spam-filter-86b21d7d1564
I hope it helps!
- 31
1
vote
Does summing up word vectors destroy their meaning?
But because the inputs have to have a fixed length
Do they? Why? The go-to strategy would be to use an RNN (possibly with LSTM or GRUs, but probably not necessary) and train it to process input ...
- 224
1
vote
How can a system recognize if two strings have the same or similar meaning?
Getting the intent of the sentence is not an easy task. To get you started on what to do, have a look on word vectors. You can also download pre-trained word2vec models. They help in getting ...
- 163
1
vote
Is there any classifier that works best in general for NLP based projects?
First of all, there are multiple factors on how well models will work. Amount of data, source of data, hyperparameters, model type, training time etc... All of these will affect the accuracy. However, ...
- 1,725
Only top scored, non community-wiki answers of a minimum length are eligible