Low-Resource Adaptation of Neural NLP Models

TL;DR

This paper investigates methods like distant supervision and transfer learning to adapt neural NLP models for low-resource scenarios, addressing challenges of limited annotated data across languages and domains.

Contribution

It introduces adapted neural NLP models and explores strategies for effective NLP in low-resource settings with minimal or no training data.

Findings

Effective adaptation of neural models for low-resource NLP tasks

Insights into transfer learning and distant supervision effectiveness

Frameworks for minimal-data NLP applications

Abstract

Real-world applications of natural language processing (NLP) are challenging. NLP models rely heavily on supervised machine learning and require large amounts of annotated data. These resources are often based on language data available in large quantities, such as English newswire. However, in real-world applications of NLP, the textual resources vary across several dimensions, such as language, dialect, topic, and genre. It is challenging to find annotated data of sufficient amount and quality. The objective of this thesis is to investigate methods for dealing with such low-resource scenarios in information extraction and natural language understanding. To this end, we study distant supervision and sequential transfer learning in various low-resource settings. We develop and adapt neural NLP models to explore a number of research questions concerning NLP tasks with minimal or no training data.