IST 664 Week 5 + 6 Key Terms

Process of understanding the meaning of text; to make sense of documents, paragraphs, sentences, and words. Can identify whether a text is based on a certain category like sports, politics, etc. based on the words in the text.

A very big dictionary of English words, but smarter that groups words into synsets. Helps computers understand not just words but meanings and connections.

The relationship between two words, in which the meaning of one of the words includes the meaning of the other word.

relation between cat and animal, pigeon and bird, orchid and flower; cat is said to be a hyponym of animal, pigeon a hyponym of bird, and orchid a hyponym of the flower

Is an automated technique that converts unstructured or semi-structured text into structured machine readable data. It enables systems to process large volumes of text and organize key information in a searchable and analyzable format.

Includes Relation and Event Extraction

Finding relationships between things in texts through:
- Handwritten patterns
- Surpervised Machine Learning
- Semi-supervised learning using bootstrapping

A statistical procedure that resamples a single data set to create many simulated samples. This process allows for the calculation of standard errors, confidence intervals, and hypothesis testing

It iteratively trains a model using a small amount of labeled data to predict labels for a large volume of unlabeled data. It combines supervised techniques (labeled data) with unsupervised techniques (unlabeled data) to improve performance without requiring full dataset annotation.

When new tuples are added, a wrong pattern produces wrong tuples, which create more wrong patterns, and the system slowly moves away from correct meaning

Finds events happening in texts (who, what, when, where, etc.).
This includes understanding dates and connecting events through time

Converting time expressions into exact calnder time.

Does this by checking date on [doc, article, etc.] and applies rules or calculations based on the date of whats been given to it.

A specialized Information Extraction (IE) technique that populates pre-defined, structured slots with relevant entities or events from unstructured text. It transforms natural language into structured data