# Feature Generation for Robust Semantic Role Labeling

## TL;DR

This paper introduces an automatic feature generation method for semantic role labeling using featlets and information gain, achieving competitive results with minimal manual effort.

## Contribution

It presents a novel automated approach to generate rich features from simple units, reducing the need for expert-designed features in semantic role labeling.

## Key findings

- Achieves state-of-the-art performance on SRL datasets
- Reduces manual feature engineering effort
- Demonstrates effectiveness of featlet-based feature generation

## Abstract

Hand-engineered feature sets are a well understood method for creating robust NLP models, but they require a lot of expertise and effort to create. In this work we describe how to automatically generate rich feature sets from simple units called featlets, requiring less engineering. Using information gain to guide the generation process, we train models which rival the state of the art on two standard Semantic Role Labeling datasets with almost no task or linguistic insight.