back to work
text-autocomplete

natural language processing

text-autocomplete

A next-word prediction interface built around an N-gram language model trained on WikiText-103.

pythonn-gramwikitext-103

metric

language model

view project

overview

A next-word prediction application that suggests the next word as you type. powered by N-gram language models trained on WikiText-103.

challenge

The goal was to learn how autocomplete system works.

approach

I trained an N-gram pipeline, tuned the prediction flow for practical suggestions, and wrapped it in a lightweight interface that reacts as the user types.

outcome

The result is a fast predictive typing demo that makes the underlying model legible, interactive, and easy to evaluate.

stack

python, n-gram language models, wikitext-103 dataset

highlights

trained on WikiText-103
real-time next-word suggestions
lightweight interface for instant feedback