Sign in
Sign in
or
Create a new account
Categories
Migration Mapping Assistant Your Saved List Partners Sell in AWS Marketplace Amazon Web Services Home Help
Amazon SageMaker ×

Amazon SageMaker is a fully-managed platform that enables developers and data scientists to quickly and easily build, train, and deploy machine learning models at any scale. With Amazon SageMaker, all the barriers and complexity that typically slow down developers who want to use machine learning are removed. The service includes models that can be used together or independently to build, train, and deploy your machine learning models.

Mphasis DeepInsights Address Extraction

By: Mphasis Latest Version: 1.3

A Deep Learning approach for address extraction from unstructured documents.

Product Overview

Address Extraction model is a robust LSTM based cognitive algorithm for extraction of address from free text. The algorithm uses Deep Learning to parse syntactic and semantic patterns for identifying various country-level addresses in the data. The algorithm ingests a text file as input and outputs all the addresses extracted from the given text file as a string separated by a comma delimiter. The model is trained on addresses from USA and Canada. It identifies and extracts addresses based on the learnt patterns of addresses in these countries.

Key Data

Version
By Mphasis
Categories
Type Model Package
Fulfillment Methods Amazon SageMaker

Usage Information

Fulfillment Methods

Amazon SageMaker

Input:

Following are the mandatory inputs for predictions made by the algorithm:

input_text : This is the path of the '.txt' file stored in S3. Ensure that the file is 'utf-8' encoded. Please follow the below instructions as well: 1) Within the content of the file, the address length must be between 5-9 words, without any special characters 2) The address must contain country name 3) In this version we extract USA and Canada address with following formats/patterns: - 1031 E 226th St Wakefield, USA - 331 E 132nd St Mott Haven, USA - 015 Matthews Ave Williamsbridge, USA - 3034 Hone Ave Baychester, USA 4) The Address extraction is purely pattern based recognition algorithm.

Supported content types for input: 'text/plain' Sample Input:

RKH Specialty Page 3 of 4 UMR: B0180 ME1706357 Fiscal and Regulatory Section TAX PAYABLE BY INSURER(S): None applicable. COUNTRY OF ORIGIN: United States of America. OVERSEAS BROKER: 331 E 132nd St Mott Haven, USA

Output:

Supported content types: 'text/csv' Sample Output:

Addresses
0, 331 E 132nd St Mott Haven, USA

Invoking endpoint:

If you are using real time inferencing, please create the endpoint first and then use the following command to invoke it:

aws sagemaker-runtime invoke-endpoint --endpoint-name $model_name --body fileb://$file_name --content-type 'text/plain' --region us-east-2 sample.csv

Substitute the following parameters:

"endpoint-name" - name of the inference endpoint where the model is deployed "input.txt"- input text file to do the inference on "text/plain" - MIME type of the given input file (above) "output.csv" - filename where the inference results are written to

Resources:

Link to Instructions Notebook: https://tinyurl.com/tqtxju9

Link to Sample Input Txt Files : https://tinyurl.com/u8fahm8

Link to Sample Output csv files https://tinyurl.com/vene8nt

Support Information

Mphasis DeepInsights Address Extraction

For any assistance, please reach out to:

https://www2.mphasis.com/AWS-Marketplace-Support-LP.html

AWS Infrastructure

AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services. Learn more

Refund Policy

Currently we do not support refunds, but you can cancel your subscription to the service at any time.

Customer Reviews