chatbot

Keras One Hot Encoding Memory Management - best Possible way out

安稳与你 提交于 2019-12-11 02:43:40
问题 I know this problem has been answered in different ways in the past. But I am not able to figure out and fit in my code and need help. I am using the cornell movie corpus as my dataset. Trying to train a LSTM model for chatbot is the final expectation. But I am stuck with initial one hot encoding and is getting out of memory. Note the VM I am training is 86GB memory but still having issues.In nmt_special_utils_mod.py the one hot encoding is going beyond allocated memory and I am not able to

How can I train an intent in Watson conversation to accept any number?

你离开我真会死。 提交于 2019-12-11 01:47:56
问题 How can we train an intent to accept numbers and identify it as that particular state? For example, I'm training an intent to accept a price. If I type: What about 560? It accepts 560 but if I just type 560 it does not identify. 回答1: If you wanna combine the intent and the entity, you can simply ADD one more condition, e.g: if bot recognizes #yourIntent AND @sys-number response: "Do you want information about @sys-number?" Or, if you want to identify the number even ONLY it is entered by the

Direct Line API - Bot Framework / Hero Cards and Attachments

試著忘記壹切 提交于 2019-12-11 01:46:11
问题 I just started using the Direct Line API (1.1) and I saw that it doesn't let you know if a conversation was showed inside a Hero Card or a Button for example. { "id": "fBPDq9JSeL|000000000000000004", "conversationId": "fBPDq9JSeL", "created": "2016-11-28T20:22:20.6035604Z", "from": "portosegurobot", "text": "Health For Pets\n\nNossa missão é proporcionar a cães e gatos uma vida mais saudável e feliz.\n\nAcesse e saiba mais\n\n(Acesse) https://health4pet.com.br/", "images": [], "attachments":

Sending an image without the link showing with discord library

梦想与她 提交于 2019-12-11 00:55:54
问题 I would like my discord bot to send an image (from a url), but have the url be hidden from the message that is sent in chat. For sending messages, im using a switch statement that only uses the writing after an "!" case 'happy': bot.sendMessage({ to: channelID, message: 'https://pictureexample.jpg' }); How would I send messages without having the link show in chat? 回答1: As user4261590 wrote, you can use embeds to achieve this. Here's an example that might work for you: case 'happy': const

Custom slot types in amazon lex without enumeration values

天大地大妈咪最大 提交于 2019-12-11 00:08:41
问题 I'm trying to build a bot to change userinfo stored in a database. My first thought was to create two slot types like {toChange} and {newValue} where the user could say "Change my name to Peter Griffin" or "My new email is user@mail.com". Turns out Lex can't handle these custom string inputs. I had to create a slot type for each value the user can have: {name} with AMAZON.Person , {address} with AMAZON.PostalAddress and so on and let Lambda handle the correct slots to elicit. The problem is

QnA maker versioning

倖福魔咒の 提交于 2019-12-10 23:23:18
问题 I am hoping to use QnA maker to facilitate the simple question and answer feature of my chatbot, and use LUIS for more complex intents like extracting entities from sentences for questions that require more context. With LUIS, it's possible to publish different versions of your app to either production or staging. It's also possible to clone and import versions. I would like to also do this with QnA Maker. Is it possible or a feature that will be added in the future? I know its possible to

LUIS - Can we use phrases list for new values in the entity type List

爷,独闯天下 提交于 2019-12-10 18:50:06
问题 I'm creating LUIS chat bot app for extracting information regarding a company. For example " what is the filed_name1 for company Google ". So I'm currently extracting " filed_name1 " using "list entity " as the number of fields for a company are limited. Similarly I'm using List entity for extracting company name.As the company names are also limited as now. Now i want to handle scenario when a new company name gets added to existing list. I've tried using " Phrases list" to check if it can

how to find similarity between two question even though the words are differentiate

青春壹個敷衍的年華 提交于 2019-12-10 12:35:00
问题 is there is any way to find the meaning of the string is similar or not,,, even though the words in the string are differentiated Till now i tried fuzzy-wuzzy,levenstein distance,cosine similarity to match the string but all are matches the words not the meaning of the words Str1 = "what are types of negotiation" Str2 = "what are advantages of negotiation" Str3 = "what are categories of negotiation" Ratio = fuzz.ratio(Str1.lower(),Str2.lower()) Partial_Ratio = fuzz.partial_ratio(Str1.lower()

CHATBOT: Programming a chatbot with Perl

倾然丶 夕夏残阳落幕 提交于 2019-12-09 23:58:10
问题 I'm studing Perl language. I think programming a chatbot would be a funny way of studing that language and learn it. The description of the chatbot I am interested in can be found here. Does anyone know any manual or website especially focused on programming chatbot in Perl language? Thank you! 回答1: See http://poe.perl.org/?POE_Cookbook - simple bot is described here: http://poe.perl.org/?POE_Cookbook/IRC_Bots Documentation for Bot::BasicBot, which is a wrapper around POE::Component::IRC.

How to store and retrieve the chat history of the dialogflow?

蹲街弑〆低调 提交于 2019-12-09 15:53:52
问题 I want to redirect the chat from Google dialogflow to a human. For this, I want to get the history of the conversation made by the user. Is there any platform where the history is being stored? If yes, how to access it. If not, how to achieve this functionality.. 回答1: There's no current API to retrieve session history. The only alternative is to save the history yourself. You can use any database you're familiar with, MySQL, MongoDB, or even a cloud hosted database such as Firebase Realtime