EMNLP 2022main4 citations

An Empirical Study on Finding Spans

Weiwei Gu, Boyuan Zheng, Yunmo Chen, Tongfei Chen, Benjamin Van Durme

Abstract

We present an empirical study on methods for span finding, the selection of consecutive tokens in text for some downstream tasks. We focus on approaches that can be employed in training end-to-end information extraction systems, and find there is no definitive solution without considering task properties, and provide our observations to help with future design choices: 1) a tagging approach often yields higher precision while span enumeration and boundary prediction provide higher recall; 2) span type information can benefit a boundary prediction approach; 3) additional contextualization does not help span finding in most cases.

BibTeX
@inproceedings{gu-etal-2022-empirical,
    title = "An Empirical Study on Finding Spans",
    author = "Gu, Weiwei  and
      Zheng, Boyuan  and
      Chen, Yunmo  and
      Chen, Tongfei  and
      Van Durme, Benjamin",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.emnlp-main.264/",
    doi = "10.18653/v1/2022.emnlp-main.264",
    pages = "3976--3983"
}