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
1
vote
1 answer

RASA: Wrong intent and entity detected if examples contains numbers as digit sequences

I have two different intents to capture body temperature and oxygen saturation values: Intent: body_temperature_data (containing body_temperature custom entity) Intent: oxygen_saturation_data (containing oxygen_saturation custom entity) Here below…
Giorgio Robino
  • 2,148
  • 6
  • 38
  • 59
1
vote
1 answer

Extract a path of dependency relations from the ROOT to a token? SPACY

Extract a path of dependency relations from the ROOT to a token? SPACY. The code I have it extract the whole path import spacy sentence = "I saw the man with a telescop" nlp = spacy.load('en') doc = nlp(sentence) for sent in doc.sents: for…
Tech News
  • 11
  • 4
1
vote
0 answers

why does sometimes alexa skills doesnt call the fallback intent with certain utterances?

I am doing working on a Alexa Math Quiz skill. So because Alexa by default doesn't handle negatives and floats I created slots for negative, result and decimal so a person could answer like this: "{result}", …
linker85
  • 1,601
  • 5
  • 26
  • 44
1
vote
1 answer

Rasa Chatbot cannot response to user input

I have using DIETClassifier for my entity extraction, and this is my pipeline: pipeline: - name: SpacyNLP model: en_core_web_sm - name: SpacyTokenizer - name: CountVectorsFeaturizer - name: CRFEntityExtractor - name: DIETClassifier …
Zahraa Maher
  • 85
  • 6
1
vote
1 answer

Visualizing a List in APL using HTTP-Endpoint for Alexa

I am currently building an Alexa Skill using my own .NET-Backend, which should return an AlexaTextList with dynamic contents from my service. The request by Alexa looks the following: { "version": "1.0", "session": { "new": false, …
Kitzng
  • 105
  • 1
  • 9
1
vote
1 answer

Detecting arbitrary amount of intents using Dialogflow

In Dialogflow (ES version), we have an intent for detecting product names and optional quantities. E.g. Do you have Pepsi or I need 4 apples. We also have some training examples that contain more than one product. E.g: I need 2 brush and 3…
Jahir
  • 630
  • 1
  • 11
  • 25
1
vote
1 answer

Analyze the whole document text using LUIS Azure Language Services

I've trained an Azure LUIS service model that takes sentences as an input, extracts the key information, and give back the JSON response. It's working fine for short sentences, now I want it to take a document (PDF, DOCX) and analyze all of the…
Farhan Mubasher
  • 166
  • 6
1
vote
1 answer

Problem with RASA Entity Extraction in a translation NLU Model

I'm new to RASA framework. I'm trying to develop a Spanish NLU model capable of classifying a user message in 4 different intents ("translation", "definition", "synonym" and "pronunciation") and recognising entities (in this case, my entities could…
Alberto Sánchez Ruiz
  • 95
  • 1
  • 9
1
vote
1 answer

'rasa run actions & rasa shell' FREEZING the terminal

When I am trying to run the command rasa run actions & rasa shell in the terminal for running rasa actions file, my terminal is freezing and the endpoint server is not starting. The terminal freezes at this point: (rasa2)…
nabajit dey
  • 11
  • 3
1
vote
1 answer

Prevent Luis.ai from recognizing 'a' or 'the' as entities

I create an pattern.any entity and intent similar to this: I want to run [salesforce] bot I want to run [facebook] bot I call my entity "BotName" and the intent "BotRun" This works fine, however, it's confusing the entity when the user enter 'a' or…
Bill Software Engineer
  • 7,362
  • 23
  • 91
  • 174
1
vote
0 answers

How good is Dialogflow at telling similar intents apart?

I'm new to Dialogflow and NLU/NLP in general. From the examples I've seen, it seems possible to train Dialogflow with just a few phrases to parse two locations as different parameters depending on context, e.g. using "from" to infer that it's…
user12687708
  • 49
  • 1
  • 6
1
vote
2 answers

What is the difference between machine learning and deep learning in building a chatbot?

To be more specific, The traditional chatbot framework consists of 3 components: NLU (1.intent classification 2. entity recognition) Dialogue Management (1. DST 2. Dialogue Policy) NLG. I am just confused that If I use a deep learning…
Charon
  • 11
  • 1
1
vote
2 answers

Using Regex with Rasa (How to recognize entities not in training examples)

I am working on a customer relations chatbot. The user can input a greeting, user name, phone number etc., I created a few training examples(50+ names) to help the chatbot in nlu.md file. But the problem is the chatbot is not able to recognize an…
Ramya PS
  • 11
  • 2
0
votes
0 answers

IBM Natural Language Understanding Tutorial Issue

I'm trying to do the "Create an artificial intelligence bookmark organizer for the Chrome browser" tutorial found AT THIS LINK I'm using a Mac. Put the folder structure together. Signed up with the IBM developer site as required. When I try to…
Robert Till
  • 1
0
votes
0 answers

Why can't my botpress NLU find the number in 1100cm?

I use Botpress V12 selfhosted. I have a NLU intent in botpress that should get the sizes of trucks out of the answer. The intent includes short and long answers to train the bot. One problem keeps occuring: the bot understands '1100 cm' but not…
Arthurio
  • 1
1
2
3 4 5