An Empirical Investigation of Contextualized Number Prediction

Taylor Berg-Kirkpatrick, Daniel Spokoyny


Abstract
We conduct a large scale empirical investigation of contextualized number prediction in running text. Specifically, we consider two tasks: (1)masked number prediction– predict-ing a missing numerical value within a sentence, and (2)numerical anomaly detection–detecting an errorful numeric value within a sentence. We experiment with novel combinations of contextual encoders and output distributions over the real number line. Specifically, we introduce a suite of output distribution parameterizations that incorporate latent variables to add expressivity and better fit the natural distribution of numeric values in running text, and combine them with both recur-rent and transformer-based encoder architectures. We evaluate these models on two numeric datasets in the financial and scientific domain. Our findings show that output distributions that incorporate discrete latent variables and allow for multiple modes outperform simple flow-based counterparts on all datasets, yielding more accurate numerical pre-diction and anomaly detection. We also show that our models effectively utilize textual con-text and benefit from general-purpose unsupervised pretraining.
Anthology ID:
2020.emnlp-main.385
Original:
2020.emnlp-main.385v1
Version 2:
2020.emnlp-main.385v2
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4754–4764
Language:
URL:
https://aclanthology.org/2020.emnlp-main.385
DOI:
10.18653/v1/2020.emnlp-main.385
Bibkey:
Cite (ACL):
Taylor Berg-Kirkpatrick and Daniel Spokoyny. 2020. An Empirical Investigation of Contextualized Number Prediction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4754–4764, Online. Association for Computational Linguistics.
Cite (Informal):
An Empirical Investigation of Contextualized Number Prediction (Berg-Kirkpatrick & Spokoyny, EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.385.pdf
Video:
 https://slideslive.com/38939346
Code
 dspoka/mnm
Data
DROP