17962364. TRANSFER LEARNING FOR SENIORITY MODELING LABEL SHORTAGE simplified abstract (Microsoft Technology Licensing, LLC)
Contents
- 1 TRANSFER LEARNING FOR SENIORITY MODELING LABEL SHORTAGE
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 TRANSFER LEARNING FOR SENIORITY MODELING LABEL SHORTAGE - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
TRANSFER LEARNING FOR SENIORITY MODELING LABEL SHORTAGE
Organization Name
Microsoft Technology Licensing, LLC
Inventor(s)
Zheng Zhang of San Carlos CA (US)
Jacob Bollinger of San Francisco CA (US)
TRANSFER LEARNING FOR SENIORITY MODELING LABEL SHORTAGE - A simplified explanation of the abstract
This abstract first appeared for US patent application 17962364 titled 'TRANSFER LEARNING FOR SENIORITY MODELING LABEL SHORTAGE
Simplified Explanation
The patent application discusses techniques for using transfer learning to address label data shortage in seniority modeling for an online service.
- Training an initialized neural network with profile data and standardized position title labels to form a pre-trained neural network.
- Training the pre-trained neural network with profile data and position seniority labels to form a fine-tuned neural network.
- Computing the position seniority for a user based on their profile data using the fine-tuned neural network.
- Using the position seniority of the user in an application of an online service.
Potential Applications
This technology could be applied in various online services where determining the seniority level of users is important for providing personalized experiences or services.
Problems Solved
This technology addresses the issue of label data shortage in seniority modeling, allowing for more accurate determination of user seniority levels based on their profile data.
Benefits
The benefits of this technology include improved accuracy in determining user seniority levels, leading to better personalized services and experiences for users of online platforms.
Potential Commercial Applications
One potential commercial application of this technology could be in online job platforms, where accurately determining the seniority level of users can help match them with relevant job opportunities.
Possible Prior Art
One possible prior art for this technology could be existing methods of transfer learning in neural networks for various applications, such as image recognition or natural language processing.
Unanswered Questions
How does this technology compare to traditional methods of seniority modeling?
This article does not provide a direct comparison between this technology and traditional methods of seniority modeling.
What are the limitations of using transfer learning in this context?
The article does not discuss any potential limitations or challenges of using transfer learning to address label data shortage in seniority modeling.
Original Abstract Submitted
Techniques for using transfer learning to address label data shortage in seniority modeling for an online service are disclosed herein. In some embodiments, a computer-implemented method comprises training an initialized neural network using training examples comprising profile data and labels for the profile data, where each label comprises a standardized position title, and the training of the initialized neural network forms a pre-trained neural network. Next, the computer system may train the pre-trained neural network using training examples comprising profile data and labels for the profile data, where the labels comprise a position seniority, and the training of the pre-trained neural network forms a fine-tuned neural network. The computer system may then compute the position seniority for a user based on profile data of the user using the fine-tuned neural network, and use the position seniority of the user in an application of an online service.
