Stanford MLab at SemEval-2021 Task 8: 48 Hours Is All You Need

Abstract

This paper presents our system for the Quantity span identification, Unit of measurement identification and Value modifier classification subtasks of the MeasEval 2021 task. The purpose of the Quantity span identification task was to locate spans of text that contain a count or measurement, consisting of a value, usually followed by a unit and occasionally additional modifiers. The goal of the modifier classification task was to determine whether an associated text fragment served to indicate range, tolerance, mean value, etc. of a quantity. The developed systems used pre-trained BERT models which were fine-tuned for the task at hand. We present our system, investigate how architectural decisions affected model predictions, and conduct an error analysis. Overall, our system placed 12 / 19 in the shared task and in the 2nd place for the Unit subcategory.

Multi-Source (Pre-)Training for Cross-Domain Measurement, Unit and Context Extraction

“…For each identified Q, an enriched prediction sample is created, thereby allowing for overlapping entities and conditioning the unit and context entity extractor on one Q at a time. For Q extraction we use binary IO-tags (Liu et al, 2021). For Task 2 we use the BIO-tagging scheme.…”