# Text Classification Components for Detecting Descriptions and Names of CAD models

## TL;DR

This paper explores text analysis techniques to improve the detection of product descriptions and names in 3D CAD model search engines, using neural network models for specialized text classification tasks.

## Contribution

It introduces the application of paragraph vectors and LSTM models for classifying and identifying product-related text in a domain-specific search engine.

## Key findings

- Paragraph vectors effectively distinguish product descriptions from other text.
- LSTM models can identify product names within sentences.
- Initial results are promising for practical deployment.

## Abstract

We apply text analysis approaches for a specialized search engine for 3D CAD models and associated products. The main goals are to distinguish between actual product descriptions and other text on a website, as well as to decide whether a given text is or contains a product name. For this we use paragraph vectors for text classification, a character-level long short-term memory network (LSTM) for a single word classification and an LSTM tagger based on word embeddings for detecting product names within sentences. Despite the need to collect bigger datasets in our specific problem domain, the first results are promising and partially fit for production use.