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.

The Influence of Grammatical Gender on the Sequence of Near-synonyms in Serbian Dictionaries in Contrast to English Thesauri

Pathways Language Model (PaLM): Scaling to 540 Billion Parameters for Breakthrough Performance – Google Research Blog

Language Model Concept behind Word Suggestion Feature, by Vitou Phy

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

Space debris - Wikipedia

Grab-and-go series: n-gram model. All in one slide to implement n-gram…, by Jesse Jing, Geek Culture

Applied Sciences, Free Full-Text

How to Make an Infographic in Under 1 Hour (2023 Guide) - Venngage

Gardner's Theory Of Multiple Intelligences

Why the C Programming Language Still Runs the World

N-Gram Language Models Explained with Examples - Analytics Yogi