DeepAI AI Chat
Log In Sign Up

Information Extraction in Illicit Domains

by   Mayank Kejriwal, et al.
USC Information Sciences Institute

Extracting useful entities and attribute values from illicit domains such as human trafficking is a challenging problem with the potential for widespread social impact. Such domains employ atypical language models, have `long tails' and suffer from the problem of concept drift. In this paper, we propose a lightweight, feature-agnostic Information Extraction (IE) paradigm specifically designed for such domains. Our approach uses raw, unlabeled text from an initial corpus, and a few (12-120) seed annotations per domain-specific attribute, to learn robust IE models for unobserved pages and websites. Empirically, we demonstrate that our approach can outperform feature-centric Conditional Random Field baselines by over 18% F-Measure on five annotated sets of real-world human trafficking datasets in both low-supervision and high-supervision settings. We also show that our approach is demonstrably robust to concept drift, and can be efficiently bootstrapped even in a serial computing environment.


page 1

page 2

page 3

page 4


Attribute Extraction from Product Titles in eCommerce

This paper presents a named entity extraction system for detecting attri...

Concept Drift Detection and Adaptation with Weak Supervision on Streaming Unlabeled Data

Concept drift in learning and classification occurs when the statistical...

Bootstrapping Domain-Specific Content Discovery on the Web

The ability to continuously discover domain-specific content from the We...

ImPaKT: A Dataset for Open-Schema Knowledge Base Construction

Large language models have ushered in a golden age of semantic parsing. ...

OpenTag: Open Attribute Value Extraction from Product Profiles

Extraction of missing attribute values is to find values describing an a...

Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition

In many scenarios, named entity recognition (NER) models severely suffer...