CLUES: A Benchmark for Learning Classifiers using Natural Language Explanations
This work addresses the challenge of enabling machines to learn from language like humans, which could reduce reliance on labeled data, though it is incremental as it builds on existing entailment-based methods.
The authors tackled the problem of training zero-shot classifiers for structured data using only natural language explanations, introducing the CLUES benchmark with 180 tasks and developing the ExEnt model, which achieved up to 18% better generalization on novel tasks compared to a baseline.
Supervised learning has traditionally focused on inductive learning by observing labeled examples of a task. In contrast, humans have the ability to learn new concepts from language. Here, we explore training zero-shot classifiers for structured data purely from language. For this, we introduce CLUES, a benchmark for Classifier Learning Using natural language ExplanationS, consisting of a range of classification tasks over structured data along with natural language supervision in the form of explanations. CLUES consists of 36 real-world and 144 synthetic classification tasks. It contains crowdsourced explanations describing real-world tasks from multiple teachers and programmatically generated explanations for the synthetic tasks. To model the influence of explanations in classifying an example, we develop ExEnt, an entailment-based model that learns classifiers using explanations. ExEnt generalizes up to 18% better (relative) on novel tasks than a baseline that does not use explanations. We delineate key challenges for automated learning from explanations, addressing which can lead to progress on CLUES in the future. Code and datasets are available at: https://clues-benchmark.github.io.