Questions tagged [text-classification]
Simply stating, text classification is all about putting a piece of text into a set of (mostly predefined) categories. This is one of the most important problems which occurs in many real world applications. For example one example of text classification would be an automated call centre which would like to categorise the complaints automatically into the most appropriate bucket of problems.
text-classification
1,679
questions
0
votes
0
answers
7
views
Classifying texts using word embeddings
I'm trying to train a model that is able to classify short texts (200-600 words per text). I got a training set with their corresponding labels, and a text might have one or more labels.
My first ...
- 742
-2
votes
0
answers
30
views
Divide a text based on Intent Analysis with NLP
I have this input from a chat:
"Set an alarm for 7:00 am and play a song by Caparezza on Spotify."
The input may contain multiple actions to do on the back-end.
I want to divide a text based ...
- 17
0
votes
0
answers
15
views
Tensorflow lite android inference error "op_context->perm->dims->data[0] != dims (3 != 2)"
My .tflite model works on python but it dosen't work well on android project.
It seems no difference between python and android.
What kinds of layer or function changes demention of input?
Standalone ...
- 1
0
votes
0
answers
49
views
Fine tune Llama 2 model with custom dataset but getting zero training loss and validation loss
My problem is that the output of training loss and validation loss is 0 for the 3 epoch
Here I am using kaggle notebook
!pip install transformers datasets torch bitsandbytes peft accelerate
import ...
2
votes
0
answers
73
views
Classify data on unstructured texts using python
I'm going to give an introduction to the project surroundings so you have some context for helping me out.
I'm trying to parse out information of german organizational charts in pdf format. Right now ...
- 31
0
votes
1
answer
55
views
Text data labeling
Task: Classify customer emails into relevant categories based on their content.
Data: DataFrame containing customer emails.
I have a dataset of customer emails stored in a data frame. Each email ...
0
votes
1
answer
44
views
Efficient Methods for Updating a BERT Sequence Classification Model with New Classes?
I have a problem finding an effective method to update the classifier layer of my text classification model to include new classes. I am working on a classification task involving brand names based on ...
- 1
0
votes
0
answers
33
views
TypeError: 'numpy.bool_' object is not iterable when working with SetFit and Optuna
I am trying to train a few shot text classifier using SetFit and Optuna. When I run my code, I get the error TypeError: 'numpy.bool_' object is not iterable.
I don't understand where the error comes ...
0
votes
1
answer
65
views
Enhance model performance in text classification task
I tried to build a model for multi-label text classification task in chinese, but the performance of the model is not good enough (about 60% accuracy), and I come for help about how to enhance it.
I ...
0
votes
0
answers
21
views
Fine-tuning pretrained model on 2 tasks with 2 labeled dataset
I am having difficulty using BERT for a sentiment analysis task that handles both aspect-based sentiment analysis (ABSA) and comment sentiment analysis. I know that using two separate classification ...
- 1
-2
votes
1
answer
24
views
How to Find accuracy of FastText model in text classification?
in machine learning, all models have the equation of accuracy while in the FastText model, we don't have please support.
- 63
1
vote
0
answers
37
views
Speeding up zero-shot headline categorization with BART on Huggingface
I’m working on a Flask web app that needs to categorize 300 headlines into 9-16 dynamic categories every hour very quickly. I'm using the Facebook BART model via Huggingface's API. My current ...
- 23
0
votes
0
answers
10
views
Can you use CreateML to extract text from a text blob?
I've been using CreateML to build a model via text classification. It needs to read in a blob of text, and extract a name from that text blob. (The blob is from an OCR result from an iPhone) The text ...
- 1,048
0
votes
1
answer
584
views
Batch and Epoch training metrics for transformers Trainer
There are several ways to get metrics for transformers.Trainer but only for the evaluation and not for the training. I read and found answers scattered in different posts such as this post.
But ...
- 75
0
votes
1
answer
331
views
True Inference with Layoutlmv3
I fine-tuned LayoutLMv3 for token classification to extract key entities. I prepared a dataset using LabelStudio to train and test, and it worked well. However, I want to know how I can get a true ...
