Character-Level Models versus Morphology in Semantic Role Labeling
This work addresses the semantic analysis capabilities of character-level models for NLP researchers, but it is incremental as it primarily analyzes existing methods.
The study compared character-level, word-level, and morphology-based models for semantic role labeling across languages, finding that character-level models perform competitively but have limitations in handling out-of-domain data and long-range dependencies.
Character-level models have become a popular approach specially for their accessibility and ability to handle unseen data. However, little is known on their ability to reveal the underlying morphological structure of a word, which is a crucial skill for high-level semantic analysis tasks, such as semantic role labeling (SRL). In this work, we train various types of SRL models that use word, character and morphology level information and analyze how performance of characters compare to words and morphology for several languages. We conduct an in-depth error analysis for each morphological typology and analyze the strengths and limitations of character-level models that relate to out-of-domain data, training data size, long range dependencies and model complexity. Our exhaustive analyses shed light on important characteristics of character-level models and their semantic capability.