Text analysis is becoming a pervasive task in many business areas. Machine Learning is the most common approach used in text analysis, and is based on statistical and mathematical models.
Bitext
Recent Posts
How to Make Machine Learning more Effective using Linguistic Analysis
[fa icon="calendar'] Sep 3, 2021 3:58:29 PM / by Bitext posted in Machine Learning, Text Analytics, Artificial Intelligence, Chatbots, Conversational AI
How to Automate the Generation of Training Data for Conversational Bots
[fa icon="calendar'] Aug 27, 2021 5:40:52 PM / by Bitext posted in NLP, Chatbots, Conversational AI, training data
Everything looks promising in the world of bots: big players are pushing platforms to build them (Google, Amazon, Facebook, Microsoft, IBM, Apple), large retail companies are adopting them (Starbucks, Domino’s, British Airways), press is excited about movies becoming reality; and we users are eager to use. However, one dark hole remains in this scenario. The bot development process.
On the Stanford parser (and Bitext parser)
[fa icon="calendar'] Aug 17, 2021 8:10:26 PM / by Bitext posted in Sentiment Analysis, Bitext
In some of our recent talks, colleagues have asked us about the Stanford parser and how it compared to Bitext technology (namely at our last workshop on Semantic Analysis of Big Data in San Francisco, and in our presentation in the Semantic Garage also in San Francisco).
What is the difference between stemming and lemmatization?
[fa icon="calendar'] Jul 7, 2021 8:54:10 PM / by Bitext posted in Machine Learning, NLP, Bitext, Natural Language, Text Analytics, Artificial Intelligence, Deep Learning, Chatbots, Stemming, AI, Multilanguage, Lemmatization, NLP for Core, NLP for Chatbots, Conversational AI
Stemming and lemmatization are methods used by search engines and chatbots to analyze the meaning behind a word. Stemming uses the stem of the word, while lemmatization uses the context in which the word is being used. We'll later go into more detailed explanations and examples.
Evaluate the Quality of your Chatbots and Conversational Agents
[fa icon="calendar'] Jun 10, 2021 4:07:00 PM / by Bitext posted in API, Machine Learning, NLP, Big Data, Bitext, Natural Language, Artificial Intelligence, Deep Learning, Chatbots, Phrase Extraction, NLG, TechCrunch, NLU, AI, Multilanguage, NLP for Core, NLP for Chatbots
It is always important to evaluate the quality of your chatbots and conversational agents in order to know the its real health, accuracy and efficiency. Chatbot accuracy can only be increased by constantly evaluating and retraining it with new data that answers your customer's queries.
Chatbots require large amounts of training data to perform correctly. If you want your chatbot to recognize a specific intent, you need to provide a large number of sentences that express that intent, usually generated by hand. This manual generation is error-prone and can cause erroneous results.
How can we solve it?
With artificially-generated data. Since Dialogflow is one of the most popular chatbot-building platforms, we chose to perform our tests using it.
What do you evaluate in your chatbots? Some ideas
[fa icon="calendar'] May 31, 2021 10:00:00 AM / by Bitext posted in Machine Learning, NLP, Big Data, Bitext, Deep Linguistic Analysis, Natural Language, Text Analytics, Artificial Intelligence, Deep Learning, Chatbots, NLU, POS tagging, AI, Multilanguage, NLP for Core, NLP for Chatbots, "Multilingual synthetic data"
In this blog we will discuss three ways of doing your chatbot evaluation by using:
- real world evaluation data
- synthetic data
- "in scope" or "out of scope" queries