PDF] Near-Synonym Choice using a 5-gram Language Model

An unsupervised statistical method for automatic choice of near-synonyms is presented and compared to the stateof-the-art and it is shown that this method outperforms two previous methods on the same task. In this work, an unsupervised statistical method for automatic choice of near-synonyms is presented and compared to the stateof-the-art. We use a 5-gram language model built from the Google Web 1T data set. The proposed method works automatically, does not require any human-annotated knowledge resources (e.g., ontologies) and can be applied to different languages. Our evaluation experiments show that this method outperforms two previous methods on the same task. We also show that our proposed unsupervised method is comparable to a supervised method on the same task. This work is applicable to an intelligent thesaurus, machine translation, and natural language generation.

PDF] Near-Synonym Choice using a 5-gram Language Model

N-Gram Model

Efficient evolution of human antibodies from general protein language models

Sample Synonym, PDF

N-gram Language Modeling in Natural Language Processing - KDnuggets

Solved Final Project N-Gram Language Models In the textbook

Large language models encode clinical knowledge

Fill and sign PDF forms using Adobe Acrobat Fill & Sign tool

The COM-B Model for Behavior Change - The Decision Lab

IS-LM Model: What It Is, IS and LM Curves, Characteristics, Limitations