A Taxonomy of Ambiguity Types for NLP

TL;DR

This paper introduces a taxonomy of ambiguity types in English to improve NLP analysis by enabling more nuanced evaluation of language models and datasets.

Contribution

It proposes a detailed taxonomy of ambiguity types in English, facilitating fine-grained analysis of NLP systems' handling of language ambiguities.

Findings

Taxonomy enables better dataset analysis

Improves assessment of model performance on ambiguity

Highlights different ambiguity resolution approaches

Abstract

Ambiguity is an critical component of language that allows for more effective communication between speakers, but is often ignored in NLP. Recent work suggests that NLP systems may struggle to grasp certain elements of human language understanding because they may not handle ambiguities at the level that humans naturally do in communication. Additionally, different types of ambiguity may serve different purposes and require different approaches for resolution, and we aim to investigate how language models' abilities vary across types. We propose a taxonomy of ambiguity types as seen in English to facilitate NLP analysis. Our taxonomy can help make meaningful splits in language ambiguity data, allowing for more fine-grained assessments of both datasets and model performance.