Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Domain Specific Data Distillation and Multi-modal Embedding Generation

Sharadind Peddiraju, Srini Rajagopal

TL;DR

This paper introduces a novel modeling approach that leverages structured data to filter noise from unstructured data, resulting in embeddings with high precision and recall for domain-specific attribute prediction.

Abstract

The challenge of creating domain-centric embeddings arises from the abundance of unstructured data and the scarcity of domain-specific structured data. Conventional embedding techniques often rely on either modality, limiting their applicability and efficacy. This paper introduces a novel modeling approach that leverages structured data to filter noise from unstructured data, resulting in embeddings with high precision and recall for domain-specific attribute prediction. The proposed model operates within a Hybrid Collaborative Filtering (HCF) framework, where generic entity representations are fine-tuned through relevant item prediction tasks. Our experiments, focusing on the cloud computing domain, demonstrate that HCF-based embeddings outperform AutoEncoder-based embeddings (using purely unstructured data), achieving a 28% lift in precision and an 11% lift in recall for domain-specific attribute prediction.

Domain Specific Data Distillation and Multi-modal Embedding Generation

TL;DR

This paper introduces a novel modeling approach that leverages structured data to filter noise from unstructured data, resulting in embeddings with high precision and recall for domain-specific attribute prediction.

Abstract

The challenge of creating domain-centric embeddings arises from the abundance of unstructured data and the scarcity of domain-specific structured data. Conventional embedding techniques often rely on either modality, limiting their applicability and efficacy. This paper introduces a novel modeling approach that leverages structured data to filter noise from unstructured data, resulting in embeddings with high precision and recall for domain-specific attribute prediction. The proposed model operates within a Hybrid Collaborative Filtering (HCF) framework, where generic entity representations are fine-tuned through relevant item prediction tasks. Our experiments, focusing on the cloud computing domain, demonstrate that HCF-based embeddings outperform AutoEncoder-based embeddings (using purely unstructured data), achieving a 28% lift in precision and an 11% lift in recall for domain-specific attribute prediction.

Paper Structure

This paper contains 19 sections, 7 equations, 3 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Creating Domain Representations
  4. Embedding Based Learning
  5. Modeling Architecture
  6. Hybrid Collaborative Filtering (HCF)
  7. Stage 1: Unsupervised Pre-Train
  8. Stage 2: Supervised Fine-Tuning
  9. Experimental Setup & Model Training
  10. Data sets
  11. Comparative Methods and Experiments Design
  12. Training & Hyper-parameter Tuning
  13. Results & Discussion
  14. Quantitative Evaluation: Tech Product Likelihood Prediction
  15. Qualitative Evaluation: Company Community Detection
  16. ...and 4 more sections

Figures (3)

  • Figure 1: HCF Model Summary
  • Figure 2: Industry Communities
  • Figure 3: Software Industry Sub-Graph