| Term . | Definition . |
|---|---|
| Artificial intelligence (AI) | The development of systems that can perform tasks requiring human-like intelligence, such as learning and problem-solving. |
| Natural language processing (NLP) | Enabling machines to understand and process human language. |
| Large language models (LLMs) | Advanced AI models for understanding, interpreting, and generating human language. |
| Named entity recognition (NER) | An NLP task that identifies and classifies named entities in text into categories. |
| BiLSTM (bidirectional long short-term memory) | A recurrent neural network that processes data in both forward and backward directions. |
| Attention mechanism | A technique allowing models to focus on specific parts of input data. |
| Transformer models | Deep learning models using self-attention mechanisms. |
| BERT (bidirectional encoder representations from transformers) | A transformer-based machine learning technique designed to better understand the context of words in search queries. |
| GPT (generative pretrained transformer) | LLM for generating human-like text. |
| ChatGPT | A GPT variant optimized for conversational applications. |
| Chatbot | Software simulating human-like conversation using AI and NLP. |
| Embedding | Converting words or phrases into vectors to represent their meaning. |
| Zero-shot learning | The ability of a model to understand and respond to tasks it has not been specifically trained on. |
| Encoder | Processes input data into a richer representation in neural networks. |
| Token | The basic unit of text processing in NLP. |
| Tokenization | The process of converting text into tokens can be fed into NLP models. |
| Fine-tuning | Adjusting a pre-trained model for a specific task. |
| Prompt engineering | Creating inputs to elicit specific responses from LLMs. |
| Precision | The measure of a model’s performance in correctly identifying only relevant instances |
| Recall | Measuring a model’s performance in capturing all relevant instances. |
| F1 score | A measure of a test’s accuracy, considering precision and recall. |
| AUC (area under the curve) | A performance metric for classification models at various threshold settings. |
| Macro-F1 score | A type of F1 score calculated by taking the average of the F1 scores per class, giving equal weight to each class. |
| Micro-F1 score | An F1 score considering the total true positives, false negatives, and false positives. |
| Cross-validation | A technique for assessing how a predictive model will generalize to an independent dataset. |
| ROC (receiver operating characteristic) curve | A graph showing the performance of a classification model at all classification thresholds. |
| Physical component summary (PCS) | A health survey score reflects a person’s physical well-being and ability to perform everyday activities. |
| Term . | Definition . |
|---|---|
| Artificial intelligence (AI) | The development of systems that can perform tasks requiring human-like intelligence, such as learning and problem-solving. |
| Natural language processing (NLP) | Enabling machines to understand and process human language. |
| Large language models (LLMs) | Advanced AI models for understanding, interpreting, and generating human language. |
| Named entity recognition (NER) | An NLP task that identifies and classifies named entities in text into categories. |
| BiLSTM (bidirectional long short-term memory) | A recurrent neural network that processes data in both forward and backward directions. |
| Attention mechanism | A technique allowing models to focus on specific parts of input data. |
| Transformer models | Deep learning models using self-attention mechanisms. |
| BERT (bidirectional encoder representations from transformers) | A transformer-based machine learning technique designed to better understand the context of words in search queries. |
| GPT (generative pretrained transformer) | LLM for generating human-like text. |
| ChatGPT | A GPT variant optimized for conversational applications. |
| Chatbot | Software simulating human-like conversation using AI and NLP. |
| Embedding | Converting words or phrases into vectors to represent their meaning. |
| Zero-shot learning | The ability of a model to understand and respond to tasks it has not been specifically trained on. |
| Encoder | Processes input data into a richer representation in neural networks. |
| Token | The basic unit of text processing in NLP. |
| Tokenization | The process of converting text into tokens can be fed into NLP models. |
| Fine-tuning | Adjusting a pre-trained model for a specific task. |
| Prompt engineering | Creating inputs to elicit specific responses from LLMs. |
| Precision | The measure of a model’s performance in correctly identifying only relevant instances |
| Recall | Measuring a model’s performance in capturing all relevant instances. |
| F1 score | A measure of a test’s accuracy, considering precision and recall. |
| AUC (area under the curve) | A performance metric for classification models at various threshold settings. |
| Macro-F1 score | A type of F1 score calculated by taking the average of the F1 scores per class, giving equal weight to each class. |
| Micro-F1 score | An F1 score considering the total true positives, false negatives, and false positives. |
| Cross-validation | A technique for assessing how a predictive model will generalize to an independent dataset. |
| ROC (receiver operating characteristic) curve | A graph showing the performance of a classification model at all classification thresholds. |
| Physical component summary (PCS) | A health survey score reflects a person’s physical well-being and ability to perform everyday activities. |
This table provides a comprehensive glossary of key terms and acronyms used in the field of AI, with a focus on NLP and LLMs.
| Term . | Definition . |
|---|---|
| Artificial intelligence (AI) | The development of systems that can perform tasks requiring human-like intelligence, such as learning and problem-solving. |
| Natural language processing (NLP) | Enabling machines to understand and process human language. |
| Large language models (LLMs) | Advanced AI models for understanding, interpreting, and generating human language. |
| Named entity recognition (NER) | An NLP task that identifies and classifies named entities in text into categories. |
| BiLSTM (bidirectional long short-term memory) | A recurrent neural network that processes data in both forward and backward directions. |
| Attention mechanism | A technique allowing models to focus on specific parts of input data. |
| Transformer models | Deep learning models using self-attention mechanisms. |
| BERT (bidirectional encoder representations from transformers) | A transformer-based machine learning technique designed to better understand the context of words in search queries. |
| GPT (generative pretrained transformer) | LLM for generating human-like text. |
| ChatGPT | A GPT variant optimized for conversational applications. |
| Chatbot | Software simulating human-like conversation using AI and NLP. |
| Embedding | Converting words or phrases into vectors to represent their meaning. |
| Zero-shot learning | The ability of a model to understand and respond to tasks it has not been specifically trained on. |
| Encoder | Processes input data into a richer representation in neural networks. |
| Token | The basic unit of text processing in NLP. |
| Tokenization | The process of converting text into tokens can be fed into NLP models. |
| Fine-tuning | Adjusting a pre-trained model for a specific task. |
| Prompt engineering | Creating inputs to elicit specific responses from LLMs. |
| Precision | The measure of a model’s performance in correctly identifying only relevant instances |
| Recall | Measuring a model’s performance in capturing all relevant instances. |
| F1 score | A measure of a test’s accuracy, considering precision and recall. |
| AUC (area under the curve) | A performance metric for classification models at various threshold settings. |
| Macro-F1 score | A type of F1 score calculated by taking the average of the F1 scores per class, giving equal weight to each class. |
| Micro-F1 score | An F1 score considering the total true positives, false negatives, and false positives. |
| Cross-validation | A technique for assessing how a predictive model will generalize to an independent dataset. |
| ROC (receiver operating characteristic) curve | A graph showing the performance of a classification model at all classification thresholds. |
| Physical component summary (PCS) | A health survey score reflects a person’s physical well-being and ability to perform everyday activities. |
| Term . | Definition . |
|---|---|
| Artificial intelligence (AI) | The development of systems that can perform tasks requiring human-like intelligence, such as learning and problem-solving. |
| Natural language processing (NLP) | Enabling machines to understand and process human language. |
| Large language models (LLMs) | Advanced AI models for understanding, interpreting, and generating human language. |
| Named entity recognition (NER) | An NLP task that identifies and classifies named entities in text into categories. |
| BiLSTM (bidirectional long short-term memory) | A recurrent neural network that processes data in both forward and backward directions. |
| Attention mechanism | A technique allowing models to focus on specific parts of input data. |
| Transformer models | Deep learning models using self-attention mechanisms. |
| BERT (bidirectional encoder representations from transformers) | A transformer-based machine learning technique designed to better understand the context of words in search queries. |
| GPT (generative pretrained transformer) | LLM for generating human-like text. |
| ChatGPT | A GPT variant optimized for conversational applications. |
| Chatbot | Software simulating human-like conversation using AI and NLP. |
| Embedding | Converting words or phrases into vectors to represent their meaning. |
| Zero-shot learning | The ability of a model to understand and respond to tasks it has not been specifically trained on. |
| Encoder | Processes input data into a richer representation in neural networks. |
| Token | The basic unit of text processing in NLP. |
| Tokenization | The process of converting text into tokens can be fed into NLP models. |
| Fine-tuning | Adjusting a pre-trained model for a specific task. |
| Prompt engineering | Creating inputs to elicit specific responses from LLMs. |
| Precision | The measure of a model’s performance in correctly identifying only relevant instances |
| Recall | Measuring a model’s performance in capturing all relevant instances. |
| F1 score | A measure of a test’s accuracy, considering precision and recall. |
| AUC (area under the curve) | A performance metric for classification models at various threshold settings. |
| Macro-F1 score | A type of F1 score calculated by taking the average of the F1 scores per class, giving equal weight to each class. |
| Micro-F1 score | An F1 score considering the total true positives, false negatives, and false positives. |
| Cross-validation | A technique for assessing how a predictive model will generalize to an independent dataset. |
| ROC (receiver operating characteristic) curve | A graph showing the performance of a classification model at all classification thresholds. |
| Physical component summary (PCS) | A health survey score reflects a person’s physical well-being and ability to perform everyday activities. |
This table provides a comprehensive glossary of key terms and acronyms used in the field of AI, with a focus on NLP and LLMs.
This PDF is available to Subscribers Only
View Article Abstract & Purchase OptionsFor full access to this pdf, sign in to an existing account, or purchase an annual subscription.
