![]() ![]() First, you would likely need a single model to classify the category and then a model for each of the categories. Without applying a zero-shot model, using a similar tree-based system may be out of reach for two main reasons. For example, a category may be "play music," and then intents for the category may be "play artist" or "play album." Some intents may be classified together, and thus, I believe it is better to first determine the category of intent and then determine the specific action(s) to perform. This article proposes a tree-based intent classification system that leverages zero-shot text classification models. It was released under an MIT license, which is a permissive licence you can read more about here. We'll use the second most downloaded zero-shot text classification model on Hugging Face's model distribution network, which was created by Facebook AI. With this technology, NLP practitioners can train their models on a single text entailment dataset and then use that model to perform text classification for any arbitrary label. So, given the text "I would like to buy an apple" and the label "food" the premise would be the text and the hypothesis would be something similar to "This text is about food." Then, the model determines if the hypothesis entails, or does not entail the premise. ![]() The input to the model is phrased as an entailment problem for each label. Zero-shot text classification Transformer models were proposed in 2019 in the paper "Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach". This article proposes a possible way to leverage new technologies to perform intent classification without any training data. For example, say you ask a chatbot, "Please play U2's newest song," then the bot must determine that the user wishes to "play a song." From there, the model would typically use entity recognition to determine which song to play. Intent classification is the act of determining which action the user wishes to perform. Intent classification is a fundamental tasks that chatbots perform. I encourage you to expand upon these ideas and possibly integrate them into your chatbot systems. If successful, this method would reduce the complexity required for developing chatbots while potentially improving their performance. But, there's a potential solution to this problem when it comes to intent classification for chatbots, and that is using zero-shot text classification Transformer models. One of the most cumbersome tasks for many natural language processing (NLP) projects is collecting and labelling training data. ![]()
0 Comments
Leave a Reply. |