Stack Overflow
Stack Overflow

Questions tagged [nlu]

Use this tag for questions concerning approaches and algorithms specific to NLU (Natural Language Understanding).

NLU (Natural Language Understanding) is a subfield of NLP (Natural Language Processing) that deals specifically with machine understanding and interpretation of human language. NLU goes beyond speech recognition to determine a user’s intent and uses machine learning models to also recognize context, syntax, language patterns and sentiment. Business applications include virtual assistants and chatbots.

63 questions
0
votes
0 answers

How to conduct targeted sentiment analysis at the target level? (IBM Watson Cognitive)

I'm trying to assess the sentiment related to specific words that appear in a body of text. Currently I'm using IBM Watson's targeted sentiment analysis (natural_language_understanding.analyze). However, if I have two target words "apple" and…
amll
  • 1
0
votes
0 answers

slot value returns None

version: "3.1" intents: - greet - goodbye - inform entities: - location slots: location: type: text mappings: - type: from_entity entity: location intent: inform actions: - action_weather responses: …
Munsif
  • 1
  • 2
0
votes
1 answer

Snips-nlu fit failed with error module 'numpy' has no attribute 'float' after following quick start

With the latest version 0.20.2 snips-nlu library on a windows 10 machine (python 3.8.15 and numpy 1.24.0), I got attribute Error when fitting the engine. What could be the issue? (nlpenv) C:\Users\one>python -m snips_nlu train sample_dataset.json…
YuMei
  • 687
  • 8
  • 19
0
votes
0 answers

Is there any way to replace all greek letters with accents with the ones without? (the need is to handle an nlu problem with greek utterances)

I am currently building a chatbot for greek users and i need to avoid adding duplicate utterances for 'with' and 'without' accent cases so as to not have a heavy model. Do you know if there is a way to replace the list of greek letters having accent…
Emma
  • 11
  • 1
0
votes
0 answers

Is adding the failed utterances to training data help in general and in a RASA NLU model?

I have a RASA NLU model to receive a sentence from user and identify its intent and entities. I have a relatively large training data set but I still have some utterances that model fails to predict. If I gather the failed utterances and add the…
Nastaran Khalili
  • 56
  • 5
0
votes
1 answer

IBM Watson NLU gives a "training validation failed. Too few samples for label class. Minimum of 5 required" Error

I am trying to train my model in IBM Watson NLU. I have to classify emails into 2 labels. The instance has been created and I am passing the correct Model ID too. model_id = model['model_id'] model_to_view =…
ting
  • 1
0
votes
1 answer

Using custom pre-trained word embeddings

I have a fairly simple script to classify intents from natural language queries working pretty well, to which I want to add a word embedding layer from a pre-trained custom model of 200 dims. I'm trying to help myself with this tutorial Keras…
Svensk
  • 1
  • 1
0
votes
0 answers

How do I resolve proper nouns when they're being addressed by only part of their name

Say I have piece of text like: Apple was founded in 1976 by Steve Jobs, Steve Wozniak and Ronald Wayne to develop and sell Wozniak's Apple I personal computer. It was incorporated by Jobs and Wozniak as Apple Computer, Inc. in 1977, and sales of…
Shrawan Sai
  • 1
  • 1
0
votes
1 answer

Using Regex to identify Entity on a Google Action Intent

I have this Intent on Google Actions with a couple of utterances: and I'm using one of the default system types: The Bank Account should always be 8 digits so I was thinking if I could use Regex on Google Actions to identify this exact entity when…
vpego
  • 145
  • 1
  • 1
  • 8
0
votes
1 answer

How to combine 2 different shaped pytorch tensors in training?

At the moment my model gives 3 output tensors. I want two of them to be more cooperative. I want to use the combination of self.dropout1(hs) and self.dropout2(cls_hs) to pass through the self.entity_out Linear Layer. The issue is mentioned 2 tensors…
Chandra Irugalbandara
  • 3
  • 2
0
votes
0 answers

Dialogflow Multi-Item Recognition

I am pretty new to Dialogflow, and I am building this food ordering chatbot. The users can say I want a chicken burrito. or I want two chicken burrito, one beef burger, two coca-cola, one french fries. but the problem I am facing now is that…
SweetPotato
  • 61
  • 1
  • 5
0
votes
1 answer

How to host a Botpress Chatbot in Heroku platform after creating it?

My Botpress chatbot is ready to get deployed. I have gone through the documentation provided in the Botpress official website about how to deploy it in the Heroku platform but couldn't figure out mot of the things. Can someone help me with it?
TASHI TSHERING BHUTIA
  • 1
0
votes
1 answer

How to extract product name from statement using RASA?

I am beginner in RASA. I want to extract the product name as entity from a statement like "Add X to cart", "Select X" or "Put X in cart". My bot is identifying the intent correctly but is unable to extract the entity. It is only able to pick…
Pola8976
  • 11
  • 5
0
votes
1 answer

dialogflow ES NLU training phrases

Trying to know how might be the proper way to upload json intents to google dialogflow ES, to better preprocess the information, i came across this doubt. What is the workflow/pipeline dialogflow NLU? Does it stem and or lemmatize the training…
mabreu0
  • 80
  • 2
  • 8
0
votes
1 answer

why input_mask is all the same number in BERT language model?

For a text classification task I applied Bert(fine tune) and the output that I got is as below: Why input_mask is all 1 ? #to_feature_map is a function. to_feature_map("hi how are you doing",0) ({'input_mask':
user14269252
  • 412
  • 4
  • 15
1 2
3
4 5