Get Started

Resource Center

You'll find useful information about our software here in the resource library. Explore technical specifications, helpful videos, case studies and frequently asked questions.

Technical Specification

Job Order and Resume Parsers

We’ve listed out the technical specifications for our job and...

Technical Specification

AI Matching Engine

Sovren has the most robust AI matching engine because we’ve...


Case Study

A top executive recruiter puts accuracy to the ultimate test.

Due to a confidentiality agreement, we can’t reveal the name of this customer, but we can share that they are...

Case Study

Vertifi Ltd. put Sovren to the test – and we were measurably faster and more accurate than the competition.

Vertifi Ltd. is a UK-based recruitment technology provider that uses a unique brand of CV Exchange technology known as “iProfile”...

A resume/CV parser is used within human resource software and on recruitment websites, job boards and portals to simplify and accelerate the application process. It does so by extracting and classifying thousands of attributes about the candidate and providing a foundation for the semantic searching of candidate data. The parser identifies hundreds of different kinds of information within a resume or CV and clearly tags each data point (for example: first name, last name, street address, city, educational degrees, employers, skills, etc.). The results may be outputted in HR-XML or JSON format. Sovren has been building this technology for over two decades.

No, Sovren is the fastest, most accurate, and most configurable parser available anywhere.

On average, about 500 milliseconds.

Essentially any non-image resume and CV format, including all of the popular job board formats and social and professional networks.

No, the Sovren resume parsing SaaS does not store any resumes.

Yes, you can use the built-in skills list, or customize a skills list with IDs that correspond directly to your system.

Yes, you can normalize company names, position titles, school names and degree types.

There are multiple output options (HR-XML, JSON, TEXT, HTML, RTF, Template).

No, the parser has auto language detection so you will never have to tell the parser what language a CV is written in.

Yes, the parser constructs a summary of who the candidate is today, a management summary, as well as average time at each employer and more.

  • Take a moment to read the entire API Documentation. This will help you understand in detail how to implement the service and what results to expect.
  • Download a sample application (available in the API Documentation page) that best suits your programming language expertise.
  • Run the sample application (entering your SaaS credentials) and start parsing away.

You should check your remaining credit balance by looking at the CreditsRemaining field in the ParseResumeResponse or ParseJobOrderResponse object after each resume or job order parse (respectively). You can also call GetAccountInfo at any time to get this information (see the API documentation for more information).

To accurately test resume parsing, please follow these rules (read Best Practices to Test Resume Parsing Software for a more in-depth look at each of these rules):

  1. IMPORTANT: Do not use resumes with fake data such as Company1; Anytown, USA; 713-555-5555. The parser very smartly ignores all such fake data.
  2. Never accept vendor-supplied resumes.
  3. Test only about 30-50 resumes per language or locale.
  4. Don't test resumes from just one source or industry or job type.
  5. Evaluate results by hand, comparing to the actual resume.
  6. Don't just test for accuracy, test for completeness.
  7. Test scalability and robustness.
  8. Test with multiple configurations.

See how do I accurately test resume parsing above and make sure you are following each of the rules for accurately testing resume parsing.

Look at the ConvertedText: Resumes that may seem very clear when looking at the original file may yield unexpected results. In many cases, this is due to the conversion from the original file format to plain text format. The most common issues are:

  • PDF documents
  • MS Word Templates
  • Images (e.g., scanned resumes)

If you are parsing a PDF document and see jumbled text, it may be corrupted. To verify this, open the file with Adobe Reader, then choose File => Save As Other => (.txt). Look at that extracted text and if it appears jumbled, then the PDF is corrupted and there is nothing that can be done with this file (see Problems With PDF Format).

Check the Parser Configuration: The parser has many settings that may be turned on or off, all of which affect the parsing results. For example, some sections such as Training are not parsed by default but you can choose to parse for this by setting the ParseTraining flag to true.

If you are parsing a foreign language resume (e.g. Chinese) and seeing values in your saved HR-XML such as "????", this means the file was parsed correctly but you have handled the reading/saving of the response incorrectly. The problem is in how you (or your SOAP library) are reading or processing the HTTP response content. The response is UTF-8 encoded, but you are reading it (or transforming it or saving it) with an ASCII or ANSI encoding somewhere along the way.

Read through Sovren's Tips for Electronic Resumes for more helpful tips.

Email support@sovren.com and be sure to include:

  • The original resume.
  • The ConvertedText.
  • The HR-XML output from the Parser.
  • A detailed explanation that specifically describes the problem.