Year: 2022
Type: conference-paper
Abstract: Anaphora resolution is an important task, which traditionally has required costly supervised training datasets for each new language, text genre, and domain.Meanwhile, prompting large language models with a few in-context examples has emerged as a promising approach to reduce labeling costs, however there are a number of challenges in applying in-context learning to resolve anaphora.In this paper, we present MICE (Mixtures of In-Context Experts), which we demonstrate is effective for few-shot anaphora resolution in the domain of scientific protocols (Tamari et al., 2021).Given only a handful of training examples, MICE combines the predictions of hundreds of in-context experts, yielding a 30% increase in F 1 score over a competitive prompt retrieval baseline.Furthermore, we show MICE can be used to train compact student models without sacrificing performance.As far as we are aware, this is the first work to present experimental results demonstrating the effectiveness of in-context learning on the task of few-shot anaphora resolution in scientific protocols.1
Authors: Nghia T. Le, Fan Bai, Alan Ritter
Institution: Georgia Institute of Technology
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4385573688